manu commited on
Commit
7be6e70
1 Parent(s): ae66b12

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/config.json +24 -0
  2. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin +3 -0
  3. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json +64 -0
  4. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json +5 -0
  5. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/tokenizer.json +0 -0
  6. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json +844 -0
  7. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/config.json +24 -0
  8. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin +3 -0
  9. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json +64 -0
  10. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json +5 -0
  11. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/tokenizer.json +0 -0
  12. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json +844 -0
  13. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/config.json +24 -0
  14. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin +3 -0
  15. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json +118 -0
  16. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json +5 -0
  17. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/tokenizer.json +0 -0
  18. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json +844 -0
  19. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/config.json +24 -0
  20. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin +3 -0
  21. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json +118 -0
  22. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json +5 -0
  23. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/tokenizer.json +0 -0
  24. DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json +844 -0
  25. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/config.json +24 -0
  26. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/hf_model/config.json +24 -0
  27. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/hf_model/pytorch_model.bin +3 -0
  28. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/hf_model/pytorch_model.bin.index.json +64 -0
  29. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/hf_model/special_tokens_map.json +5 -0
  30. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/hf_model/tokenizer.json +0 -0
  31. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/hf_model/tokenizer_config.json +844 -0
  32. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin +3 -0
  33. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json +64 -0
  34. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json +5 -0
  35. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/tokenizer.json +0 -0
  36. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json +844 -0
  37. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/config.json +24 -0
  38. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin +3 -0
  39. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json +64 -0
  40. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json +5 -0
  41. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/tokenizer.json +0 -0
  42. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json +844 -0
  43. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/config.json +24 -0
  44. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin +3 -0
  45. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json +118 -0
  46. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json +5 -0
  47. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/tokenizer.json +0 -0
  48. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json +844 -0
  49. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/config.json +24 -0
  50. DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/hf_model/config.json +24 -0
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 512,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 2048,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 8,
14
+ "num_hidden_layers": 6,
15
+ "num_key_value_heads": 8,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "rope_theta": 10000.0,
20
+ "tie_word_embeddings": false,
21
+ "transformers_version": "4.33.3",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cc9a08bc3ac810bea2ee411a8ab63fddbd65b3c89fc456e080ee8022156a6d0
3
+ size 250646829
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "weight_map": {
3
+ "model.embed_tokens.weight": "pytorch_model.bin",
4
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model.bin",
5
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model.bin",
6
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model.bin",
7
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model.bin",
8
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model.bin",
9
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model.bin",
11
+ "model.layers.0.input_layernorm.weight": "pytorch_model.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model.bin",
13
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model.bin",
14
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model.bin",
15
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model.bin",
16
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model.bin",
17
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model.bin",
18
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model.bin",
20
+ "model.layers.1.input_layernorm.weight": "pytorch_model.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model.bin",
22
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model.bin",
23
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model.bin",
24
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model.bin",
25
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model.bin",
26
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model.bin",
27
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model.bin",
28
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model.bin",
29
+ "model.layers.2.input_layernorm.weight": "pytorch_model.bin",
30
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model.bin",
31
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model.bin",
32
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model.bin",
33
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model.bin",
34
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model.bin",
35
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model.bin",
36
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model.bin",
37
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model.bin",
38
+ "model.layers.3.input_layernorm.weight": "pytorch_model.bin",
39
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model.bin",
40
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model.bin",
41
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model.bin",
42
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model.bin",
43
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model.bin",
44
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model.bin",
45
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model.bin",
46
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model.bin",
47
+ "model.layers.4.input_layernorm.weight": "pytorch_model.bin",
48
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model.bin",
49
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model.bin",
50
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model.bin",
51
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model.bin",
52
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model.bin",
53
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model.bin",
54
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model.bin",
55
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model.bin",
56
+ "model.layers.5.input_layernorm.weight": "pytorch_model.bin",
57
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model.bin",
58
+ "model.norm.weight": "pytorch_model.bin",
59
+ "lm_head.weight": "pytorch_model.bin"
60
+ },
61
+ "metadata": {
62
+ "total_size": 231761920
63
+ }
64
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json ADDED
@@ -0,0 +1,844 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "10": {
20
+ "content": "<extra_id_6>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
28
+ "content": "<extra_id_96>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "101": {
36
+ "content": "<extra_id_97>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "102": {
44
+ "content": "<extra_id_98>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "103": {
52
+ "content": "<extra_id_99>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "11": {
60
+ "content": "<extra_id_7>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "12": {
68
+ "content": "<extra_id_8>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "13": {
76
+ "content": "<extra_id_9>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "14": {
84
+ "content": "<extra_id_10>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "15": {
92
+ "content": "<extra_id_11>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "16": {
100
+ "content": "<extra_id_12>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "17": {
108
+ "content": "<extra_id_13>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "18": {
116
+ "content": "<extra_id_14>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "19": {
124
+ "content": "<extra_id_15>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "2": {
132
+ "content": "</s>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "20": {
140
+ "content": "<extra_id_16>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "21": {
148
+ "content": "<extra_id_17>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "22": {
156
+ "content": "<extra_id_18>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "23": {
164
+ "content": "<extra_id_19>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "24": {
172
+ "content": "<extra_id_20>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "25": {
180
+ "content": "<extra_id_21>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "26": {
188
+ "content": "<extra_id_22>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "27": {
196
+ "content": "<extra_id_23>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "28": {
204
+ "content": "<extra_id_24>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "29": {
212
+ "content": "<extra_id_25>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "3": {
220
+ "content": "<pad>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "30": {
228
+ "content": "<extra_id_26>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "31": {
236
+ "content": "<extra_id_27>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32": {
244
+ "content": "<extra_id_28>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "33": {
252
+ "content": "<extra_id_29>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "34": {
260
+ "content": "<extra_id_30>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "35": {
268
+ "content": "<extra_id_31>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "36": {
276
+ "content": "<extra_id_32>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "37": {
284
+ "content": "<extra_id_33>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "38": {
292
+ "content": "<extra_id_34>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "39": {
300
+ "content": "<extra_id_35>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "4": {
308
+ "content": "<extra_id_0>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "40": {
316
+ "content": "<extra_id_36>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "41": {
324
+ "content": "<extra_id_37>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "42": {
332
+ "content": "<extra_id_38>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "43": {
340
+ "content": "<extra_id_39>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "44": {
348
+ "content": "<extra_id_40>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "45": {
356
+ "content": "<extra_id_41>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "46": {
364
+ "content": "<extra_id_42>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "47": {
372
+ "content": "<extra_id_43>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "48": {
380
+ "content": "<extra_id_44>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "49": {
388
+ "content": "<extra_id_45>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "5": {
396
+ "content": "<extra_id_1>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "50": {
404
+ "content": "<extra_id_46>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "51": {
412
+ "content": "<extra_id_47>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "52": {
420
+ "content": "<extra_id_48>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "53": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "54": {
436
+ "content": "<extra_id_50>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "55": {
444
+ "content": "<extra_id_51>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "56": {
452
+ "content": "<extra_id_52>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "57": {
460
+ "content": "<extra_id_53>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "58": {
468
+ "content": "<extra_id_54>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "59": {
476
+ "content": "<extra_id_55>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "6": {
484
+ "content": "<extra_id_2>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "60": {
492
+ "content": "<extra_id_56>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "61": {
500
+ "content": "<extra_id_57>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "62": {
508
+ "content": "<extra_id_58>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "63": {
516
+ "content": "<extra_id_59>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "64": {
524
+ "content": "<extra_id_60>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "65": {
532
+ "content": "<extra_id_61>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "66": {
540
+ "content": "<extra_id_62>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "67": {
548
+ "content": "<extra_id_63>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "68": {
556
+ "content": "<extra_id_64>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "69": {
564
+ "content": "<extra_id_65>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "7": {
572
+ "content": "<extra_id_3>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "70": {
580
+ "content": "<extra_id_66>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "71": {
588
+ "content": "<extra_id_67>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "72": {
596
+ "content": "<extra_id_68>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "73": {
604
+ "content": "<extra_id_69>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "74": {
612
+ "content": "<extra_id_70>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "75": {
620
+ "content": "<extra_id_71>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "76": {
628
+ "content": "<extra_id_72>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "77": {
636
+ "content": "<extra_id_73>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "78": {
644
+ "content": "<extra_id_74>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "79": {
652
+ "content": "<extra_id_75>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "8": {
660
+ "content": "<extra_id_4>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "80": {
668
+ "content": "<extra_id_76>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "81": {
676
+ "content": "<extra_id_77>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "82": {
684
+ "content": "<extra_id_78>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "83": {
692
+ "content": "<extra_id_79>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "84": {
700
+ "content": "<extra_id_80>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "85": {
708
+ "content": "<extra_id_81>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "86": {
716
+ "content": "<extra_id_82>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "87": {
724
+ "content": "<extra_id_83>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "88": {
732
+ "content": "<extra_id_84>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "89": {
740
+ "content": "<extra_id_85>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "9": {
748
+ "content": "<extra_id_5>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "90": {
756
+ "content": "<extra_id_86>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "91": {
764
+ "content": "<extra_id_87>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "92": {
772
+ "content": "<extra_id_88>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "93": {
780
+ "content": "<extra_id_89>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "94": {
788
+ "content": "<extra_id_90>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "95": {
796
+ "content": "<extra_id_91>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "96": {
804
+ "content": "<extra_id_92>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "97": {
812
+ "content": "<extra_id_93>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "98": {
820
+ "content": "<extra_id_94>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "99": {
828
+ "content": "<extra_id_95>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ }
835
+ },
836
+ "additional_special_tokens": [],
837
+ "bos_token": "<s>",
838
+ "clean_up_tokenization_spaces": false,
839
+ "eos_token": "</s>",
840
+ "model_max_length": 1000000000000000019884624838656,
841
+ "tokenizer_class": "LlamaTokenizer",
842
+ "unk_token": "<unk>",
843
+ "use_default_system_prompt": true
844
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 1024,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 4096,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 8,
14
+ "num_hidden_layers": 6,
15
+ "num_key_value_heads": 8,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "rope_theta": 10000.0,
20
+ "tie_word_embeddings": false,
21
+ "transformers_version": "4.33.3",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d10def0328f326457a494f9ec7427e34d9ff83760bb4edc588525da14c77025
3
+ size 740358445
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "weight_map": {
3
+ "model.embed_tokens.weight": "pytorch_model.bin",
4
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model.bin",
5
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model.bin",
6
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model.bin",
7
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model.bin",
8
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model.bin",
9
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model.bin",
11
+ "model.layers.0.input_layernorm.weight": "pytorch_model.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model.bin",
13
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model.bin",
14
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model.bin",
15
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model.bin",
16
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model.bin",
17
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model.bin",
18
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model.bin",
20
+ "model.layers.1.input_layernorm.weight": "pytorch_model.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model.bin",
22
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model.bin",
23
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model.bin",
24
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model.bin",
25
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model.bin",
26
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model.bin",
27
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model.bin",
28
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model.bin",
29
+ "model.layers.2.input_layernorm.weight": "pytorch_model.bin",
30
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model.bin",
31
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model.bin",
32
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model.bin",
33
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model.bin",
34
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model.bin",
35
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model.bin",
36
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model.bin",
37
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model.bin",
38
+ "model.layers.3.input_layernorm.weight": "pytorch_model.bin",
39
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model.bin",
40
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model.bin",
41
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model.bin",
42
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model.bin",
43
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model.bin",
44
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model.bin",
45
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model.bin",
46
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model.bin",
47
+ "model.layers.4.input_layernorm.weight": "pytorch_model.bin",
48
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model.bin",
49
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model.bin",
50
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model.bin",
51
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model.bin",
52
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model.bin",
53
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model.bin",
54
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model.bin",
55
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model.bin",
56
+ "model.layers.5.input_layernorm.weight": "pytorch_model.bin",
57
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model.bin",
58
+ "model.norm.weight": "pytorch_model.bin",
59
+ "lm_head.weight": "pytorch_model.bin"
60
+ },
61
+ "metadata": {
62
+ "total_size": 664850432
63
+ }
64
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json ADDED
@@ -0,0 +1,844 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "10": {
20
+ "content": "<extra_id_6>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
28
+ "content": "<extra_id_96>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "101": {
36
+ "content": "<extra_id_97>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "102": {
44
+ "content": "<extra_id_98>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "103": {
52
+ "content": "<extra_id_99>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "11": {
60
+ "content": "<extra_id_7>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "12": {
68
+ "content": "<extra_id_8>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "13": {
76
+ "content": "<extra_id_9>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "14": {
84
+ "content": "<extra_id_10>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "15": {
92
+ "content": "<extra_id_11>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "16": {
100
+ "content": "<extra_id_12>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "17": {
108
+ "content": "<extra_id_13>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "18": {
116
+ "content": "<extra_id_14>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "19": {
124
+ "content": "<extra_id_15>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "2": {
132
+ "content": "</s>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "20": {
140
+ "content": "<extra_id_16>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "21": {
148
+ "content": "<extra_id_17>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "22": {
156
+ "content": "<extra_id_18>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "23": {
164
+ "content": "<extra_id_19>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "24": {
172
+ "content": "<extra_id_20>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "25": {
180
+ "content": "<extra_id_21>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "26": {
188
+ "content": "<extra_id_22>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "27": {
196
+ "content": "<extra_id_23>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "28": {
204
+ "content": "<extra_id_24>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "29": {
212
+ "content": "<extra_id_25>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "3": {
220
+ "content": "<pad>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "30": {
228
+ "content": "<extra_id_26>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "31": {
236
+ "content": "<extra_id_27>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32": {
244
+ "content": "<extra_id_28>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "33": {
252
+ "content": "<extra_id_29>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "34": {
260
+ "content": "<extra_id_30>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "35": {
268
+ "content": "<extra_id_31>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "36": {
276
+ "content": "<extra_id_32>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "37": {
284
+ "content": "<extra_id_33>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "38": {
292
+ "content": "<extra_id_34>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "39": {
300
+ "content": "<extra_id_35>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "4": {
308
+ "content": "<extra_id_0>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "40": {
316
+ "content": "<extra_id_36>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "41": {
324
+ "content": "<extra_id_37>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "42": {
332
+ "content": "<extra_id_38>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "43": {
340
+ "content": "<extra_id_39>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "44": {
348
+ "content": "<extra_id_40>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "45": {
356
+ "content": "<extra_id_41>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "46": {
364
+ "content": "<extra_id_42>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "47": {
372
+ "content": "<extra_id_43>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "48": {
380
+ "content": "<extra_id_44>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "49": {
388
+ "content": "<extra_id_45>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "5": {
396
+ "content": "<extra_id_1>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "50": {
404
+ "content": "<extra_id_46>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "51": {
412
+ "content": "<extra_id_47>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "52": {
420
+ "content": "<extra_id_48>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "53": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "54": {
436
+ "content": "<extra_id_50>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "55": {
444
+ "content": "<extra_id_51>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "56": {
452
+ "content": "<extra_id_52>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "57": {
460
+ "content": "<extra_id_53>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "58": {
468
+ "content": "<extra_id_54>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "59": {
476
+ "content": "<extra_id_55>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "6": {
484
+ "content": "<extra_id_2>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "60": {
492
+ "content": "<extra_id_56>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "61": {
500
+ "content": "<extra_id_57>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "62": {
508
+ "content": "<extra_id_58>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "63": {
516
+ "content": "<extra_id_59>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "64": {
524
+ "content": "<extra_id_60>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "65": {
532
+ "content": "<extra_id_61>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "66": {
540
+ "content": "<extra_id_62>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "67": {
548
+ "content": "<extra_id_63>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "68": {
556
+ "content": "<extra_id_64>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "69": {
564
+ "content": "<extra_id_65>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "7": {
572
+ "content": "<extra_id_3>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "70": {
580
+ "content": "<extra_id_66>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "71": {
588
+ "content": "<extra_id_67>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "72": {
596
+ "content": "<extra_id_68>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "73": {
604
+ "content": "<extra_id_69>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "74": {
612
+ "content": "<extra_id_70>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "75": {
620
+ "content": "<extra_id_71>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "76": {
628
+ "content": "<extra_id_72>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "77": {
636
+ "content": "<extra_id_73>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "78": {
644
+ "content": "<extra_id_74>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "79": {
652
+ "content": "<extra_id_75>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "8": {
660
+ "content": "<extra_id_4>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "80": {
668
+ "content": "<extra_id_76>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "81": {
676
+ "content": "<extra_id_77>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "82": {
684
+ "content": "<extra_id_78>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "83": {
692
+ "content": "<extra_id_79>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "84": {
700
+ "content": "<extra_id_80>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "85": {
708
+ "content": "<extra_id_81>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "86": {
716
+ "content": "<extra_id_82>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "87": {
724
+ "content": "<extra_id_83>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "88": {
732
+ "content": "<extra_id_84>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "89": {
740
+ "content": "<extra_id_85>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "9": {
748
+ "content": "<extra_id_5>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "90": {
756
+ "content": "<extra_id_86>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "91": {
764
+ "content": "<extra_id_87>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "92": {
772
+ "content": "<extra_id_88>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "93": {
780
+ "content": "<extra_id_89>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "94": {
788
+ "content": "<extra_id_90>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "95": {
796
+ "content": "<extra_id_91>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "96": {
804
+ "content": "<extra_id_92>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "97": {
812
+ "content": "<extra_id_93>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "98": {
820
+ "content": "<extra_id_94>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "99": {
828
+ "content": "<extra_id_95>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ }
835
+ },
836
+ "additional_special_tokens": [],
837
+ "bos_token": "<s>",
838
+ "clean_up_tokenization_spaces": false,
839
+ "eos_token": "</s>",
840
+ "model_max_length": 1000000000000000019884624838656,
841
+ "tokenizer_class": "LlamaTokenizer",
842
+ "unk_token": "<unk>",
843
+ "use_default_system_prompt": true
844
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 1024,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 4128,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 8,
14
+ "num_hidden_layers": 12,
15
+ "num_key_value_heads": 8,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "rope_theta": 10000.0,
20
+ "tie_word_embeddings": false,
21
+ "transformers_version": "4.33.3",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:668dd8e82921397ffd353f733718831f118daf53b5b03b0346523b8edf34417d
3
+ size 1223286947
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "weight_map": {
3
+ "model.embed_tokens.weight": "pytorch_model.bin",
4
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model.bin",
5
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model.bin",
6
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model.bin",
7
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model.bin",
8
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model.bin",
9
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model.bin",
11
+ "model.layers.0.input_layernorm.weight": "pytorch_model.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model.bin",
13
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model.bin",
14
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model.bin",
15
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model.bin",
16
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model.bin",
17
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model.bin",
18
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model.bin",
20
+ "model.layers.1.input_layernorm.weight": "pytorch_model.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model.bin",
22
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model.bin",
23
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model.bin",
24
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model.bin",
25
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model.bin",
26
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model.bin",
27
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model.bin",
28
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model.bin",
29
+ "model.layers.2.input_layernorm.weight": "pytorch_model.bin",
30
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model.bin",
31
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model.bin",
32
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model.bin",
33
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model.bin",
34
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model.bin",
35
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model.bin",
36
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model.bin",
37
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model.bin",
38
+ "model.layers.3.input_layernorm.weight": "pytorch_model.bin",
39
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model.bin",
40
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model.bin",
41
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model.bin",
42
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model.bin",
43
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model.bin",
44
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model.bin",
45
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model.bin",
46
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model.bin",
47
+ "model.layers.4.input_layernorm.weight": "pytorch_model.bin",
48
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model.bin",
49
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model.bin",
50
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model.bin",
51
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model.bin",
52
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model.bin",
53
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model.bin",
54
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model.bin",
55
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model.bin",
56
+ "model.layers.5.input_layernorm.weight": "pytorch_model.bin",
57
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model.bin",
58
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model.bin",
59
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model.bin",
60
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model.bin",
61
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model.bin",
62
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model.bin",
63
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model.bin",
64
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model.bin",
65
+ "model.layers.6.input_layernorm.weight": "pytorch_model.bin",
66
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model.bin",
67
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model.bin",
68
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model.bin",
69
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model.bin",
70
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model.bin",
71
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model.bin",
72
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model.bin",
73
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model.bin",
74
+ "model.layers.7.input_layernorm.weight": "pytorch_model.bin",
75
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model.bin",
76
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model.bin",
77
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model.bin",
78
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model.bin",
79
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model.bin",
80
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model.bin",
81
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model.bin",
82
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model.bin",
83
+ "model.layers.8.input_layernorm.weight": "pytorch_model.bin",
84
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model.bin",
85
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model.bin",
86
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model.bin",
87
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model.bin",
88
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model.bin",
89
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model.bin",
90
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model.bin",
91
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model.bin",
92
+ "model.layers.9.input_layernorm.weight": "pytorch_model.bin",
93
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model.bin",
94
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model.bin",
95
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model.bin",
96
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model.bin",
97
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model.bin",
98
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model.bin",
99
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model.bin",
100
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model.bin",
101
+ "model.layers.10.input_layernorm.weight": "pytorch_model.bin",
102
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model.bin",
103
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model.bin",
104
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model.bin",
105
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model.bin",
106
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model.bin",
107
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model.bin",
108
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model.bin",
109
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model.bin",
110
+ "model.layers.11.input_layernorm.weight": "pytorch_model.bin",
111
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model.bin",
112
+ "model.norm.weight": "pytorch_model.bin",
113
+ "lm_head.weight": "pytorch_model.bin"
114
+ },
115
+ "metadata": {
116
+ "total_size": 1072271360
117
+ }
118
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json ADDED
@@ -0,0 +1,844 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "10": {
20
+ "content": "<extra_id_6>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
28
+ "content": "<extra_id_96>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "101": {
36
+ "content": "<extra_id_97>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "102": {
44
+ "content": "<extra_id_98>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "103": {
52
+ "content": "<extra_id_99>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "11": {
60
+ "content": "<extra_id_7>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "12": {
68
+ "content": "<extra_id_8>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "13": {
76
+ "content": "<extra_id_9>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "14": {
84
+ "content": "<extra_id_10>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "15": {
92
+ "content": "<extra_id_11>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "16": {
100
+ "content": "<extra_id_12>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "17": {
108
+ "content": "<extra_id_13>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "18": {
116
+ "content": "<extra_id_14>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "19": {
124
+ "content": "<extra_id_15>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "2": {
132
+ "content": "</s>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "20": {
140
+ "content": "<extra_id_16>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "21": {
148
+ "content": "<extra_id_17>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "22": {
156
+ "content": "<extra_id_18>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "23": {
164
+ "content": "<extra_id_19>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "24": {
172
+ "content": "<extra_id_20>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "25": {
180
+ "content": "<extra_id_21>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "26": {
188
+ "content": "<extra_id_22>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "27": {
196
+ "content": "<extra_id_23>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "28": {
204
+ "content": "<extra_id_24>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "29": {
212
+ "content": "<extra_id_25>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "3": {
220
+ "content": "<pad>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "30": {
228
+ "content": "<extra_id_26>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "31": {
236
+ "content": "<extra_id_27>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32": {
244
+ "content": "<extra_id_28>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "33": {
252
+ "content": "<extra_id_29>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "34": {
260
+ "content": "<extra_id_30>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "35": {
268
+ "content": "<extra_id_31>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "36": {
276
+ "content": "<extra_id_32>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "37": {
284
+ "content": "<extra_id_33>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "38": {
292
+ "content": "<extra_id_34>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "39": {
300
+ "content": "<extra_id_35>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "4": {
308
+ "content": "<extra_id_0>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "40": {
316
+ "content": "<extra_id_36>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "41": {
324
+ "content": "<extra_id_37>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "42": {
332
+ "content": "<extra_id_38>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "43": {
340
+ "content": "<extra_id_39>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "44": {
348
+ "content": "<extra_id_40>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "45": {
356
+ "content": "<extra_id_41>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "46": {
364
+ "content": "<extra_id_42>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "47": {
372
+ "content": "<extra_id_43>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "48": {
380
+ "content": "<extra_id_44>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "49": {
388
+ "content": "<extra_id_45>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "5": {
396
+ "content": "<extra_id_1>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "50": {
404
+ "content": "<extra_id_46>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "51": {
412
+ "content": "<extra_id_47>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "52": {
420
+ "content": "<extra_id_48>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "53": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "54": {
436
+ "content": "<extra_id_50>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "55": {
444
+ "content": "<extra_id_51>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "56": {
452
+ "content": "<extra_id_52>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "57": {
460
+ "content": "<extra_id_53>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "58": {
468
+ "content": "<extra_id_54>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "59": {
476
+ "content": "<extra_id_55>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "6": {
484
+ "content": "<extra_id_2>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "60": {
492
+ "content": "<extra_id_56>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "61": {
500
+ "content": "<extra_id_57>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "62": {
508
+ "content": "<extra_id_58>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "63": {
516
+ "content": "<extra_id_59>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "64": {
524
+ "content": "<extra_id_60>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "65": {
532
+ "content": "<extra_id_61>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "66": {
540
+ "content": "<extra_id_62>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "67": {
548
+ "content": "<extra_id_63>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "68": {
556
+ "content": "<extra_id_64>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "69": {
564
+ "content": "<extra_id_65>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "7": {
572
+ "content": "<extra_id_3>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "70": {
580
+ "content": "<extra_id_66>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "71": {
588
+ "content": "<extra_id_67>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "72": {
596
+ "content": "<extra_id_68>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "73": {
604
+ "content": "<extra_id_69>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "74": {
612
+ "content": "<extra_id_70>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "75": {
620
+ "content": "<extra_id_71>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "76": {
628
+ "content": "<extra_id_72>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "77": {
636
+ "content": "<extra_id_73>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "78": {
644
+ "content": "<extra_id_74>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "79": {
652
+ "content": "<extra_id_75>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "8": {
660
+ "content": "<extra_id_4>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "80": {
668
+ "content": "<extra_id_76>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "81": {
676
+ "content": "<extra_id_77>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "82": {
684
+ "content": "<extra_id_78>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "83": {
692
+ "content": "<extra_id_79>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "84": {
700
+ "content": "<extra_id_80>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "85": {
708
+ "content": "<extra_id_81>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "86": {
716
+ "content": "<extra_id_82>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "87": {
724
+ "content": "<extra_id_83>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "88": {
732
+ "content": "<extra_id_84>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "89": {
740
+ "content": "<extra_id_85>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "9": {
748
+ "content": "<extra_id_5>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "90": {
756
+ "content": "<extra_id_86>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "91": {
764
+ "content": "<extra_id_87>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "92": {
772
+ "content": "<extra_id_88>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "93": {
780
+ "content": "<extra_id_89>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "94": {
788
+ "content": "<extra_id_90>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "95": {
796
+ "content": "<extra_id_91>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "96": {
804
+ "content": "<extra_id_92>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "97": {
812
+ "content": "<extra_id_93>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "98": {
820
+ "content": "<extra_id_94>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "99": {
828
+ "content": "<extra_id_95>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ }
835
+ },
836
+ "additional_special_tokens": [],
837
+ "bos_token": "<s>",
838
+ "clean_up_tokenization_spaces": false,
839
+ "eos_token": "</s>",
840
+ "model_max_length": 1000000000000000019884624838656,
841
+ "tokenizer_class": "LlamaTokenizer",
842
+ "unk_token": "<unk>",
843
+ "use_default_system_prompt": true
844
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 1536,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 4128,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 12,
14
+ "num_hidden_layers": 12,
15
+ "num_key_value_heads": 12,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "rope_theta": 10000.0,
20
+ "tie_word_embeddings": false,
21
+ "transformers_version": "4.33.3",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cc9bcbba1333bce82f4b3ce47b3b113633e44e5d8f621ee025843f8acc30da3
3
+ size 2099161251
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "weight_map": {
3
+ "model.embed_tokens.weight": "pytorch_model.bin",
4
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model.bin",
5
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model.bin",
6
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model.bin",
7
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model.bin",
8
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model.bin",
9
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model.bin",
11
+ "model.layers.0.input_layernorm.weight": "pytorch_model.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model.bin",
13
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model.bin",
14
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model.bin",
15
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model.bin",
16
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model.bin",
17
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model.bin",
18
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model.bin",
20
+ "model.layers.1.input_layernorm.weight": "pytorch_model.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model.bin",
22
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model.bin",
23
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model.bin",
24
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model.bin",
25
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model.bin",
26
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model.bin",
27
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model.bin",
28
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model.bin",
29
+ "model.layers.2.input_layernorm.weight": "pytorch_model.bin",
30
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model.bin",
31
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model.bin",
32
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model.bin",
33
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model.bin",
34
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model.bin",
35
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model.bin",
36
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model.bin",
37
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model.bin",
38
+ "model.layers.3.input_layernorm.weight": "pytorch_model.bin",
39
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model.bin",
40
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model.bin",
41
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model.bin",
42
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model.bin",
43
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model.bin",
44
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model.bin",
45
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model.bin",
46
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model.bin",
47
+ "model.layers.4.input_layernorm.weight": "pytorch_model.bin",
48
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model.bin",
49
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model.bin",
50
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model.bin",
51
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model.bin",
52
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model.bin",
53
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model.bin",
54
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model.bin",
55
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model.bin",
56
+ "model.layers.5.input_layernorm.weight": "pytorch_model.bin",
57
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model.bin",
58
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model.bin",
59
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model.bin",
60
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model.bin",
61
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model.bin",
62
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model.bin",
63
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model.bin",
64
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model.bin",
65
+ "model.layers.6.input_layernorm.weight": "pytorch_model.bin",
66
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model.bin",
67
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model.bin",
68
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model.bin",
69
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model.bin",
70
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model.bin",
71
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model.bin",
72
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model.bin",
73
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model.bin",
74
+ "model.layers.7.input_layernorm.weight": "pytorch_model.bin",
75
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model.bin",
76
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model.bin",
77
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model.bin",
78
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model.bin",
79
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model.bin",
80
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model.bin",
81
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model.bin",
82
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model.bin",
83
+ "model.layers.8.input_layernorm.weight": "pytorch_model.bin",
84
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model.bin",
85
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model.bin",
86
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model.bin",
87
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model.bin",
88
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model.bin",
89
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model.bin",
90
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model.bin",
91
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model.bin",
92
+ "model.layers.9.input_layernorm.weight": "pytorch_model.bin",
93
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model.bin",
94
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model.bin",
95
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model.bin",
96
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model.bin",
97
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model.bin",
98
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model.bin",
99
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model.bin",
100
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model.bin",
101
+ "model.layers.10.input_layernorm.weight": "pytorch_model.bin",
102
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model.bin",
103
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model.bin",
104
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model.bin",
105
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model.bin",
106
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model.bin",
107
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model.bin",
108
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model.bin",
109
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model.bin",
110
+ "model.layers.11.input_layernorm.weight": "pytorch_model.bin",
111
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model.bin",
112
+ "model.norm.weight": "pytorch_model.bin",
113
+ "lm_head.weight": "pytorch_model.bin"
114
+ },
115
+ "metadata": {
116
+ "total_size": 1759401984
117
+ }
118
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
DSAutotuneConfig.false+DataMix.enplus+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json ADDED
@@ -0,0 +1,844 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "10": {
20
+ "content": "<extra_id_6>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
28
+ "content": "<extra_id_96>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "101": {
36
+ "content": "<extra_id_97>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "102": {
44
+ "content": "<extra_id_98>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "103": {
52
+ "content": "<extra_id_99>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "11": {
60
+ "content": "<extra_id_7>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "12": {
68
+ "content": "<extra_id_8>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "13": {
76
+ "content": "<extra_id_9>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "14": {
84
+ "content": "<extra_id_10>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "15": {
92
+ "content": "<extra_id_11>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "16": {
100
+ "content": "<extra_id_12>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "17": {
108
+ "content": "<extra_id_13>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "18": {
116
+ "content": "<extra_id_14>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "19": {
124
+ "content": "<extra_id_15>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "2": {
132
+ "content": "</s>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "20": {
140
+ "content": "<extra_id_16>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "21": {
148
+ "content": "<extra_id_17>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "22": {
156
+ "content": "<extra_id_18>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "23": {
164
+ "content": "<extra_id_19>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "24": {
172
+ "content": "<extra_id_20>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "25": {
180
+ "content": "<extra_id_21>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "26": {
188
+ "content": "<extra_id_22>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "27": {
196
+ "content": "<extra_id_23>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "28": {
204
+ "content": "<extra_id_24>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "29": {
212
+ "content": "<extra_id_25>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "3": {
220
+ "content": "<pad>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "30": {
228
+ "content": "<extra_id_26>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "31": {
236
+ "content": "<extra_id_27>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32": {
244
+ "content": "<extra_id_28>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "33": {
252
+ "content": "<extra_id_29>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "34": {
260
+ "content": "<extra_id_30>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "35": {
268
+ "content": "<extra_id_31>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "36": {
276
+ "content": "<extra_id_32>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "37": {
284
+ "content": "<extra_id_33>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "38": {
292
+ "content": "<extra_id_34>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "39": {
300
+ "content": "<extra_id_35>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "4": {
308
+ "content": "<extra_id_0>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "40": {
316
+ "content": "<extra_id_36>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "41": {
324
+ "content": "<extra_id_37>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "42": {
332
+ "content": "<extra_id_38>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "43": {
340
+ "content": "<extra_id_39>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "44": {
348
+ "content": "<extra_id_40>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "45": {
356
+ "content": "<extra_id_41>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "46": {
364
+ "content": "<extra_id_42>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "47": {
372
+ "content": "<extra_id_43>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "48": {
380
+ "content": "<extra_id_44>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "49": {
388
+ "content": "<extra_id_45>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "5": {
396
+ "content": "<extra_id_1>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "50": {
404
+ "content": "<extra_id_46>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "51": {
412
+ "content": "<extra_id_47>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "52": {
420
+ "content": "<extra_id_48>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "53": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "54": {
436
+ "content": "<extra_id_50>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "55": {
444
+ "content": "<extra_id_51>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "56": {
452
+ "content": "<extra_id_52>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "57": {
460
+ "content": "<extra_id_53>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "58": {
468
+ "content": "<extra_id_54>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "59": {
476
+ "content": "<extra_id_55>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "6": {
484
+ "content": "<extra_id_2>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "60": {
492
+ "content": "<extra_id_56>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "61": {
500
+ "content": "<extra_id_57>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "62": {
508
+ "content": "<extra_id_58>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "63": {
516
+ "content": "<extra_id_59>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "64": {
524
+ "content": "<extra_id_60>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "65": {
532
+ "content": "<extra_id_61>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "66": {
540
+ "content": "<extra_id_62>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "67": {
548
+ "content": "<extra_id_63>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "68": {
556
+ "content": "<extra_id_64>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "69": {
564
+ "content": "<extra_id_65>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "7": {
572
+ "content": "<extra_id_3>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "70": {
580
+ "content": "<extra_id_66>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "71": {
588
+ "content": "<extra_id_67>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "72": {
596
+ "content": "<extra_id_68>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "73": {
604
+ "content": "<extra_id_69>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "74": {
612
+ "content": "<extra_id_70>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "75": {
620
+ "content": "<extra_id_71>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "76": {
628
+ "content": "<extra_id_72>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "77": {
636
+ "content": "<extra_id_73>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "78": {
644
+ "content": "<extra_id_74>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "79": {
652
+ "content": "<extra_id_75>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "8": {
660
+ "content": "<extra_id_4>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "80": {
668
+ "content": "<extra_id_76>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "81": {
676
+ "content": "<extra_id_77>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "82": {
684
+ "content": "<extra_id_78>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "83": {
692
+ "content": "<extra_id_79>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "84": {
700
+ "content": "<extra_id_80>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "85": {
708
+ "content": "<extra_id_81>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "86": {
716
+ "content": "<extra_id_82>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "87": {
724
+ "content": "<extra_id_83>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "88": {
732
+ "content": "<extra_id_84>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "89": {
740
+ "content": "<extra_id_85>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "9": {
748
+ "content": "<extra_id_5>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "90": {
756
+ "content": "<extra_id_86>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "91": {
764
+ "content": "<extra_id_87>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "92": {
772
+ "content": "<extra_id_88>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "93": {
780
+ "content": "<extra_id_89>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "94": {
788
+ "content": "<extra_id_90>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "95": {
796
+ "content": "<extra_id_91>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "96": {
804
+ "content": "<extra_id_92>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "97": {
812
+ "content": "<extra_id_93>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "98": {
820
+ "content": "<extra_id_94>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "99": {
828
+ "content": "<extra_id_95>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ }
835
+ },
836
+ "additional_special_tokens": [],
837
+ "bos_token": "<s>",
838
+ "clean_up_tokenization_spaces": false,
839
+ "eos_token": "</s>",
840
+ "model_max_length": 1000000000000000019884624838656,
841
+ "tokenizer_class": "LlamaTokenizer",
842
+ "unk_token": "<unk>",
843
+ "use_default_system_prompt": true
844
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 512,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 2048,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 8,
14
+ "num_hidden_layers": 6,
15
+ "num_key_value_heads": 8,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "rope_theta": 10000.0,
20
+ "tie_word_embeddings": false,
21
+ "transformers_version": "4.33.3",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/hf_model/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 512,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 2048,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 8,
14
+ "num_hidden_layers": 6,
15
+ "num_key_value_heads": 8,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "rope_theta": 10000.0,
20
+ "tie_word_embeddings": false,
21
+ "transformers_version": "4.33.3",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/hf_model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e62825a8621ab7c22ecdb15b5898eaa1cd482a77706e11083ffc90e1abe68d
3
+ size 250646829
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/hf_model/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "weight_map": {
3
+ "model.embed_tokens.weight": "pytorch_model.bin",
4
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model.bin",
5
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model.bin",
6
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model.bin",
7
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model.bin",
8
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model.bin",
9
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model.bin",
11
+ "model.layers.0.input_layernorm.weight": "pytorch_model.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model.bin",
13
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model.bin",
14
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model.bin",
15
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model.bin",
16
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model.bin",
17
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model.bin",
18
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model.bin",
20
+ "model.layers.1.input_layernorm.weight": "pytorch_model.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model.bin",
22
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model.bin",
23
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model.bin",
24
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model.bin",
25
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model.bin",
26
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model.bin",
27
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model.bin",
28
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model.bin",
29
+ "model.layers.2.input_layernorm.weight": "pytorch_model.bin",
30
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model.bin",
31
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model.bin",
32
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model.bin",
33
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model.bin",
34
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model.bin",
35
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model.bin",
36
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model.bin",
37
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model.bin",
38
+ "model.layers.3.input_layernorm.weight": "pytorch_model.bin",
39
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model.bin",
40
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model.bin",
41
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model.bin",
42
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model.bin",
43
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model.bin",
44
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model.bin",
45
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model.bin",
46
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model.bin",
47
+ "model.layers.4.input_layernorm.weight": "pytorch_model.bin",
48
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model.bin",
49
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model.bin",
50
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model.bin",
51
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model.bin",
52
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model.bin",
53
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model.bin",
54
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model.bin",
55
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model.bin",
56
+ "model.layers.5.input_layernorm.weight": "pytorch_model.bin",
57
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model.bin",
58
+ "model.norm.weight": "pytorch_model.bin",
59
+ "lm_head.weight": "pytorch_model.bin"
60
+ },
61
+ "metadata": {
62
+ "total_size": 231761920
63
+ }
64
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/hf_model/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/hf_model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/hf_model/tokenizer_config.json ADDED
@@ -0,0 +1,844 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "10": {
20
+ "content": "<extra_id_6>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
28
+ "content": "<extra_id_96>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "101": {
36
+ "content": "<extra_id_97>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "102": {
44
+ "content": "<extra_id_98>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "103": {
52
+ "content": "<extra_id_99>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "11": {
60
+ "content": "<extra_id_7>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "12": {
68
+ "content": "<extra_id_8>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "13": {
76
+ "content": "<extra_id_9>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "14": {
84
+ "content": "<extra_id_10>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "15": {
92
+ "content": "<extra_id_11>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "16": {
100
+ "content": "<extra_id_12>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "17": {
108
+ "content": "<extra_id_13>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "18": {
116
+ "content": "<extra_id_14>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "19": {
124
+ "content": "<extra_id_15>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "2": {
132
+ "content": "</s>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "20": {
140
+ "content": "<extra_id_16>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "21": {
148
+ "content": "<extra_id_17>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "22": {
156
+ "content": "<extra_id_18>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "23": {
164
+ "content": "<extra_id_19>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "24": {
172
+ "content": "<extra_id_20>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "25": {
180
+ "content": "<extra_id_21>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "26": {
188
+ "content": "<extra_id_22>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "27": {
196
+ "content": "<extra_id_23>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "28": {
204
+ "content": "<extra_id_24>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "29": {
212
+ "content": "<extra_id_25>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "3": {
220
+ "content": "<pad>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "30": {
228
+ "content": "<extra_id_26>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "31": {
236
+ "content": "<extra_id_27>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32": {
244
+ "content": "<extra_id_28>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "33": {
252
+ "content": "<extra_id_29>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "34": {
260
+ "content": "<extra_id_30>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "35": {
268
+ "content": "<extra_id_31>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "36": {
276
+ "content": "<extra_id_32>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "37": {
284
+ "content": "<extra_id_33>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "38": {
292
+ "content": "<extra_id_34>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "39": {
300
+ "content": "<extra_id_35>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "4": {
308
+ "content": "<extra_id_0>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "40": {
316
+ "content": "<extra_id_36>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "41": {
324
+ "content": "<extra_id_37>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "42": {
332
+ "content": "<extra_id_38>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "43": {
340
+ "content": "<extra_id_39>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "44": {
348
+ "content": "<extra_id_40>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "45": {
356
+ "content": "<extra_id_41>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "46": {
364
+ "content": "<extra_id_42>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "47": {
372
+ "content": "<extra_id_43>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "48": {
380
+ "content": "<extra_id_44>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "49": {
388
+ "content": "<extra_id_45>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "5": {
396
+ "content": "<extra_id_1>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "50": {
404
+ "content": "<extra_id_46>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "51": {
412
+ "content": "<extra_id_47>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "52": {
420
+ "content": "<extra_id_48>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "53": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "54": {
436
+ "content": "<extra_id_50>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "55": {
444
+ "content": "<extra_id_51>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "56": {
452
+ "content": "<extra_id_52>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "57": {
460
+ "content": "<extra_id_53>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "58": {
468
+ "content": "<extra_id_54>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "59": {
476
+ "content": "<extra_id_55>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "6": {
484
+ "content": "<extra_id_2>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "60": {
492
+ "content": "<extra_id_56>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "61": {
500
+ "content": "<extra_id_57>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "62": {
508
+ "content": "<extra_id_58>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "63": {
516
+ "content": "<extra_id_59>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "64": {
524
+ "content": "<extra_id_60>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "65": {
532
+ "content": "<extra_id_61>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "66": {
540
+ "content": "<extra_id_62>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "67": {
548
+ "content": "<extra_id_63>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "68": {
556
+ "content": "<extra_id_64>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "69": {
564
+ "content": "<extra_id_65>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "7": {
572
+ "content": "<extra_id_3>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "70": {
580
+ "content": "<extra_id_66>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "71": {
588
+ "content": "<extra_id_67>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "72": {
596
+ "content": "<extra_id_68>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "73": {
604
+ "content": "<extra_id_69>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "74": {
612
+ "content": "<extra_id_70>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "75": {
620
+ "content": "<extra_id_71>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "76": {
628
+ "content": "<extra_id_72>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "77": {
636
+ "content": "<extra_id_73>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "78": {
644
+ "content": "<extra_id_74>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "79": {
652
+ "content": "<extra_id_75>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "8": {
660
+ "content": "<extra_id_4>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "80": {
668
+ "content": "<extra_id_76>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "81": {
676
+ "content": "<extra_id_77>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "82": {
684
+ "content": "<extra_id_78>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "83": {
692
+ "content": "<extra_id_79>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "84": {
700
+ "content": "<extra_id_80>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "85": {
708
+ "content": "<extra_id_81>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "86": {
716
+ "content": "<extra_id_82>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "87": {
724
+ "content": "<extra_id_83>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "88": {
732
+ "content": "<extra_id_84>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "89": {
740
+ "content": "<extra_id_85>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "9": {
748
+ "content": "<extra_id_5>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "90": {
756
+ "content": "<extra_id_86>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "91": {
764
+ "content": "<extra_id_87>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "92": {
772
+ "content": "<extra_id_88>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "93": {
780
+ "content": "<extra_id_89>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "94": {
788
+ "content": "<extra_id_90>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "95": {
796
+ "content": "<extra_id_91>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "96": {
804
+ "content": "<extra_id_92>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "97": {
812
+ "content": "<extra_id_93>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "98": {
820
+ "content": "<extra_id_94>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "99": {
828
+ "content": "<extra_id_95>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ }
835
+ },
836
+ "additional_special_tokens": [],
837
+ "bos_token": "<s>",
838
+ "clean_up_tokenization_spaces": false,
839
+ "eos_token": "</s>",
840
+ "model_max_length": 1000000000000000019884624838656,
841
+ "tokenizer_class": "LlamaTokenizer",
842
+ "unk_token": "<unk>",
843
+ "use_default_system_prompt": true
844
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8e62825a8621ab7c22ecdb15b5898eaa1cd482a77706e11083ffc90e1abe68d
3
+ size 250646829
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "weight_map": {
3
+ "model.embed_tokens.weight": "pytorch_model.bin",
4
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model.bin",
5
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model.bin",
6
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model.bin",
7
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model.bin",
8
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model.bin",
9
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model.bin",
11
+ "model.layers.0.input_layernorm.weight": "pytorch_model.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model.bin",
13
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model.bin",
14
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model.bin",
15
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model.bin",
16
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model.bin",
17
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model.bin",
18
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model.bin",
20
+ "model.layers.1.input_layernorm.weight": "pytorch_model.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model.bin",
22
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model.bin",
23
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model.bin",
24
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model.bin",
25
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model.bin",
26
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model.bin",
27
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model.bin",
28
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model.bin",
29
+ "model.layers.2.input_layernorm.weight": "pytorch_model.bin",
30
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model.bin",
31
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model.bin",
32
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model.bin",
33
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model.bin",
34
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model.bin",
35
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model.bin",
36
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model.bin",
37
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model.bin",
38
+ "model.layers.3.input_layernorm.weight": "pytorch_model.bin",
39
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model.bin",
40
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model.bin",
41
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model.bin",
42
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model.bin",
43
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model.bin",
44
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model.bin",
45
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model.bin",
46
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model.bin",
47
+ "model.layers.4.input_layernorm.weight": "pytorch_model.bin",
48
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model.bin",
49
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model.bin",
50
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model.bin",
51
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model.bin",
52
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model.bin",
53
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model.bin",
54
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model.bin",
55
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model.bin",
56
+ "model.layers.5.input_layernorm.weight": "pytorch_model.bin",
57
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model.bin",
58
+ "model.norm.weight": "pytorch_model.bin",
59
+ "lm_head.weight": "pytorch_model.bin"
60
+ },
61
+ "metadata": {
62
+ "total_size": 231761920
63
+ }
64
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small1+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json ADDED
@@ -0,0 +1,844 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "10": {
20
+ "content": "<extra_id_6>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
28
+ "content": "<extra_id_96>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "101": {
36
+ "content": "<extra_id_97>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "102": {
44
+ "content": "<extra_id_98>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "103": {
52
+ "content": "<extra_id_99>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "11": {
60
+ "content": "<extra_id_7>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "12": {
68
+ "content": "<extra_id_8>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "13": {
76
+ "content": "<extra_id_9>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "14": {
84
+ "content": "<extra_id_10>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "15": {
92
+ "content": "<extra_id_11>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "16": {
100
+ "content": "<extra_id_12>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "17": {
108
+ "content": "<extra_id_13>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "18": {
116
+ "content": "<extra_id_14>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "19": {
124
+ "content": "<extra_id_15>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "2": {
132
+ "content": "</s>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "20": {
140
+ "content": "<extra_id_16>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "21": {
148
+ "content": "<extra_id_17>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "22": {
156
+ "content": "<extra_id_18>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "23": {
164
+ "content": "<extra_id_19>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "24": {
172
+ "content": "<extra_id_20>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "25": {
180
+ "content": "<extra_id_21>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "26": {
188
+ "content": "<extra_id_22>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "27": {
196
+ "content": "<extra_id_23>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "28": {
204
+ "content": "<extra_id_24>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "29": {
212
+ "content": "<extra_id_25>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "3": {
220
+ "content": "<pad>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "30": {
228
+ "content": "<extra_id_26>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "31": {
236
+ "content": "<extra_id_27>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32": {
244
+ "content": "<extra_id_28>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "33": {
252
+ "content": "<extra_id_29>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "34": {
260
+ "content": "<extra_id_30>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "35": {
268
+ "content": "<extra_id_31>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "36": {
276
+ "content": "<extra_id_32>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "37": {
284
+ "content": "<extra_id_33>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "38": {
292
+ "content": "<extra_id_34>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "39": {
300
+ "content": "<extra_id_35>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "4": {
308
+ "content": "<extra_id_0>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "40": {
316
+ "content": "<extra_id_36>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "41": {
324
+ "content": "<extra_id_37>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "42": {
332
+ "content": "<extra_id_38>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "43": {
340
+ "content": "<extra_id_39>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "44": {
348
+ "content": "<extra_id_40>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "45": {
356
+ "content": "<extra_id_41>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "46": {
364
+ "content": "<extra_id_42>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "47": {
372
+ "content": "<extra_id_43>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "48": {
380
+ "content": "<extra_id_44>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "49": {
388
+ "content": "<extra_id_45>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "5": {
396
+ "content": "<extra_id_1>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "50": {
404
+ "content": "<extra_id_46>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "51": {
412
+ "content": "<extra_id_47>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "52": {
420
+ "content": "<extra_id_48>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "53": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "54": {
436
+ "content": "<extra_id_50>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "55": {
444
+ "content": "<extra_id_51>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "56": {
452
+ "content": "<extra_id_52>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "57": {
460
+ "content": "<extra_id_53>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "58": {
468
+ "content": "<extra_id_54>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "59": {
476
+ "content": "<extra_id_55>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "6": {
484
+ "content": "<extra_id_2>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "60": {
492
+ "content": "<extra_id_56>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "61": {
500
+ "content": "<extra_id_57>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "62": {
508
+ "content": "<extra_id_58>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "63": {
516
+ "content": "<extra_id_59>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "64": {
524
+ "content": "<extra_id_60>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "65": {
532
+ "content": "<extra_id_61>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "66": {
540
+ "content": "<extra_id_62>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "67": {
548
+ "content": "<extra_id_63>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "68": {
556
+ "content": "<extra_id_64>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "69": {
564
+ "content": "<extra_id_65>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "7": {
572
+ "content": "<extra_id_3>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "70": {
580
+ "content": "<extra_id_66>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "71": {
588
+ "content": "<extra_id_67>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "72": {
596
+ "content": "<extra_id_68>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "73": {
604
+ "content": "<extra_id_69>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "74": {
612
+ "content": "<extra_id_70>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "75": {
620
+ "content": "<extra_id_71>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "76": {
628
+ "content": "<extra_id_72>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "77": {
636
+ "content": "<extra_id_73>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "78": {
644
+ "content": "<extra_id_74>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "79": {
652
+ "content": "<extra_id_75>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "8": {
660
+ "content": "<extra_id_4>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "80": {
668
+ "content": "<extra_id_76>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "81": {
676
+ "content": "<extra_id_77>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "82": {
684
+ "content": "<extra_id_78>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "83": {
692
+ "content": "<extra_id_79>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "84": {
700
+ "content": "<extra_id_80>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "85": {
708
+ "content": "<extra_id_81>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "86": {
716
+ "content": "<extra_id_82>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "87": {
724
+ "content": "<extra_id_83>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "88": {
732
+ "content": "<extra_id_84>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "89": {
740
+ "content": "<extra_id_85>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "9": {
748
+ "content": "<extra_id_5>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "90": {
756
+ "content": "<extra_id_86>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "91": {
764
+ "content": "<extra_id_87>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "92": {
772
+ "content": "<extra_id_88>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "93": {
780
+ "content": "<extra_id_89>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "94": {
788
+ "content": "<extra_id_90>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "95": {
796
+ "content": "<extra_id_91>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "96": {
804
+ "content": "<extra_id_92>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "97": {
812
+ "content": "<extra_id_93>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "98": {
820
+ "content": "<extra_id_94>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "99": {
828
+ "content": "<extra_id_95>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ }
835
+ },
836
+ "additional_special_tokens": [],
837
+ "bos_token": "<s>",
838
+ "clean_up_tokenization_spaces": false,
839
+ "eos_token": "</s>",
840
+ "model_max_length": 1000000000000000019884624838656,
841
+ "tokenizer_class": "LlamaTokenizer",
842
+ "unk_token": "<unk>",
843
+ "use_default_system_prompt": true
844
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 1024,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 4096,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 8,
14
+ "num_hidden_layers": 6,
15
+ "num_key_value_heads": 8,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "rope_theta": 10000.0,
20
+ "tie_word_embeddings": false,
21
+ "transformers_version": "4.33.3",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10dc345155f2a727e1308b994fb1f5016551f1e6d7b10532ea6da5ceb8b9d992
3
+ size 740358445
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "weight_map": {
3
+ "model.embed_tokens.weight": "pytorch_model.bin",
4
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model.bin",
5
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model.bin",
6
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model.bin",
7
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model.bin",
8
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model.bin",
9
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model.bin",
11
+ "model.layers.0.input_layernorm.weight": "pytorch_model.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model.bin",
13
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model.bin",
14
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model.bin",
15
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model.bin",
16
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model.bin",
17
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model.bin",
18
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model.bin",
20
+ "model.layers.1.input_layernorm.weight": "pytorch_model.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model.bin",
22
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model.bin",
23
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model.bin",
24
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model.bin",
25
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model.bin",
26
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model.bin",
27
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model.bin",
28
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model.bin",
29
+ "model.layers.2.input_layernorm.weight": "pytorch_model.bin",
30
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model.bin",
31
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model.bin",
32
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model.bin",
33
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model.bin",
34
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model.bin",
35
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model.bin",
36
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model.bin",
37
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model.bin",
38
+ "model.layers.3.input_layernorm.weight": "pytorch_model.bin",
39
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model.bin",
40
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model.bin",
41
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model.bin",
42
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model.bin",
43
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model.bin",
44
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model.bin",
45
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model.bin",
46
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model.bin",
47
+ "model.layers.4.input_layernorm.weight": "pytorch_model.bin",
48
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model.bin",
49
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model.bin",
50
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model.bin",
51
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model.bin",
52
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model.bin",
53
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model.bin",
54
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model.bin",
55
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model.bin",
56
+ "model.layers.5.input_layernorm.weight": "pytorch_model.bin",
57
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model.bin",
58
+ "model.norm.weight": "pytorch_model.bin",
59
+ "lm_head.weight": "pytorch_model.bin"
60
+ },
61
+ "metadata": {
62
+ "total_size": 664850432
63
+ }
64
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small2+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json ADDED
@@ -0,0 +1,844 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "10": {
20
+ "content": "<extra_id_6>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
28
+ "content": "<extra_id_96>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "101": {
36
+ "content": "<extra_id_97>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "102": {
44
+ "content": "<extra_id_98>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "103": {
52
+ "content": "<extra_id_99>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "11": {
60
+ "content": "<extra_id_7>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "12": {
68
+ "content": "<extra_id_8>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "13": {
76
+ "content": "<extra_id_9>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "14": {
84
+ "content": "<extra_id_10>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "15": {
92
+ "content": "<extra_id_11>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "16": {
100
+ "content": "<extra_id_12>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "17": {
108
+ "content": "<extra_id_13>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "18": {
116
+ "content": "<extra_id_14>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "19": {
124
+ "content": "<extra_id_15>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "2": {
132
+ "content": "</s>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "20": {
140
+ "content": "<extra_id_16>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "21": {
148
+ "content": "<extra_id_17>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "22": {
156
+ "content": "<extra_id_18>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "23": {
164
+ "content": "<extra_id_19>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "24": {
172
+ "content": "<extra_id_20>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "25": {
180
+ "content": "<extra_id_21>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "26": {
188
+ "content": "<extra_id_22>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "27": {
196
+ "content": "<extra_id_23>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "28": {
204
+ "content": "<extra_id_24>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "29": {
212
+ "content": "<extra_id_25>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "3": {
220
+ "content": "<pad>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "30": {
228
+ "content": "<extra_id_26>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "31": {
236
+ "content": "<extra_id_27>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32": {
244
+ "content": "<extra_id_28>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "33": {
252
+ "content": "<extra_id_29>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "34": {
260
+ "content": "<extra_id_30>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "35": {
268
+ "content": "<extra_id_31>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "36": {
276
+ "content": "<extra_id_32>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "37": {
284
+ "content": "<extra_id_33>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "38": {
292
+ "content": "<extra_id_34>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "39": {
300
+ "content": "<extra_id_35>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "4": {
308
+ "content": "<extra_id_0>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "40": {
316
+ "content": "<extra_id_36>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "41": {
324
+ "content": "<extra_id_37>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "42": {
332
+ "content": "<extra_id_38>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "43": {
340
+ "content": "<extra_id_39>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "44": {
348
+ "content": "<extra_id_40>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "45": {
356
+ "content": "<extra_id_41>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "46": {
364
+ "content": "<extra_id_42>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "47": {
372
+ "content": "<extra_id_43>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "48": {
380
+ "content": "<extra_id_44>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "49": {
388
+ "content": "<extra_id_45>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "5": {
396
+ "content": "<extra_id_1>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "50": {
404
+ "content": "<extra_id_46>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "51": {
412
+ "content": "<extra_id_47>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "52": {
420
+ "content": "<extra_id_48>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "53": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "54": {
436
+ "content": "<extra_id_50>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "55": {
444
+ "content": "<extra_id_51>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "56": {
452
+ "content": "<extra_id_52>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "57": {
460
+ "content": "<extra_id_53>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "58": {
468
+ "content": "<extra_id_54>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "59": {
476
+ "content": "<extra_id_55>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "6": {
484
+ "content": "<extra_id_2>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "60": {
492
+ "content": "<extra_id_56>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "61": {
500
+ "content": "<extra_id_57>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "62": {
508
+ "content": "<extra_id_58>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "63": {
516
+ "content": "<extra_id_59>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "64": {
524
+ "content": "<extra_id_60>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "65": {
532
+ "content": "<extra_id_61>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "66": {
540
+ "content": "<extra_id_62>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "67": {
548
+ "content": "<extra_id_63>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "68": {
556
+ "content": "<extra_id_64>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "69": {
564
+ "content": "<extra_id_65>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "7": {
572
+ "content": "<extra_id_3>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "70": {
580
+ "content": "<extra_id_66>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "71": {
588
+ "content": "<extra_id_67>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "72": {
596
+ "content": "<extra_id_68>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "73": {
604
+ "content": "<extra_id_69>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "74": {
612
+ "content": "<extra_id_70>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "75": {
620
+ "content": "<extra_id_71>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "76": {
628
+ "content": "<extra_id_72>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "77": {
636
+ "content": "<extra_id_73>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "78": {
644
+ "content": "<extra_id_74>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "79": {
652
+ "content": "<extra_id_75>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "8": {
660
+ "content": "<extra_id_4>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "80": {
668
+ "content": "<extra_id_76>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "81": {
676
+ "content": "<extra_id_77>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "82": {
684
+ "content": "<extra_id_78>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "83": {
692
+ "content": "<extra_id_79>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "84": {
700
+ "content": "<extra_id_80>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "85": {
708
+ "content": "<extra_id_81>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "86": {
716
+ "content": "<extra_id_82>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "87": {
724
+ "content": "<extra_id_83>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "88": {
732
+ "content": "<extra_id_84>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "89": {
740
+ "content": "<extra_id_85>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "9": {
748
+ "content": "<extra_id_5>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "90": {
756
+ "content": "<extra_id_86>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "91": {
764
+ "content": "<extra_id_87>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "92": {
772
+ "content": "<extra_id_88>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "93": {
780
+ "content": "<extra_id_89>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "94": {
788
+ "content": "<extra_id_90>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "95": {
796
+ "content": "<extra_id_91>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "96": {
804
+ "content": "<extra_id_92>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "97": {
812
+ "content": "<extra_id_93>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "98": {
820
+ "content": "<extra_id_94>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "99": {
828
+ "content": "<extra_id_95>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ }
835
+ },
836
+ "additional_special_tokens": [],
837
+ "bos_token": "<s>",
838
+ "clean_up_tokenization_spaces": false,
839
+ "eos_token": "</s>",
840
+ "model_max_length": 1000000000000000019884624838656,
841
+ "tokenizer_class": "LlamaTokenizer",
842
+ "unk_token": "<unk>",
843
+ "use_default_system_prompt": true
844
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 1024,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 4128,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 8,
14
+ "num_hidden_layers": 12,
15
+ "num_key_value_heads": 8,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "rope_theta": 10000.0,
20
+ "tie_word_embeddings": false,
21
+ "transformers_version": "4.33.3",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3492303ecec824493ca12dc7b023344cf3c00b45ab18f48ed6a76ae115676e50
3
+ size 1223286947
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/pytorch_model.bin.index.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "weight_map": {
3
+ "model.embed_tokens.weight": "pytorch_model.bin",
4
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model.bin",
5
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model.bin",
6
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model.bin",
7
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model.bin",
8
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model.bin",
9
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model.bin",
10
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model.bin",
11
+ "model.layers.0.input_layernorm.weight": "pytorch_model.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model.bin",
13
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model.bin",
14
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model.bin",
15
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model.bin",
16
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model.bin",
17
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model.bin",
18
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model.bin",
20
+ "model.layers.1.input_layernorm.weight": "pytorch_model.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model.bin",
22
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model.bin",
23
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model.bin",
24
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model.bin",
25
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model.bin",
26
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model.bin",
27
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model.bin",
28
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model.bin",
29
+ "model.layers.2.input_layernorm.weight": "pytorch_model.bin",
30
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model.bin",
31
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model.bin",
32
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model.bin",
33
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model.bin",
34
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model.bin",
35
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model.bin",
36
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model.bin",
37
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model.bin",
38
+ "model.layers.3.input_layernorm.weight": "pytorch_model.bin",
39
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model.bin",
40
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model.bin",
41
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model.bin",
42
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model.bin",
43
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model.bin",
44
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model.bin",
45
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model.bin",
46
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model.bin",
47
+ "model.layers.4.input_layernorm.weight": "pytorch_model.bin",
48
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model.bin",
49
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model.bin",
50
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model.bin",
51
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model.bin",
52
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model.bin",
53
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model.bin",
54
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model.bin",
55
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model.bin",
56
+ "model.layers.5.input_layernorm.weight": "pytorch_model.bin",
57
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model.bin",
58
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model.bin",
59
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model.bin",
60
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model.bin",
61
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model.bin",
62
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model.bin",
63
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model.bin",
64
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model.bin",
65
+ "model.layers.6.input_layernorm.weight": "pytorch_model.bin",
66
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model.bin",
67
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model.bin",
68
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model.bin",
69
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model.bin",
70
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model.bin",
71
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model.bin",
72
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model.bin",
73
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model.bin",
74
+ "model.layers.7.input_layernorm.weight": "pytorch_model.bin",
75
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model.bin",
76
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model.bin",
77
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model.bin",
78
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model.bin",
79
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model.bin",
80
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model.bin",
81
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model.bin",
82
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model.bin",
83
+ "model.layers.8.input_layernorm.weight": "pytorch_model.bin",
84
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model.bin",
85
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model.bin",
86
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model.bin",
87
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model.bin",
88
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model.bin",
89
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model.bin",
90
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model.bin",
91
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model.bin",
92
+ "model.layers.9.input_layernorm.weight": "pytorch_model.bin",
93
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model.bin",
94
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model.bin",
95
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model.bin",
96
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model.bin",
97
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model.bin",
98
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model.bin",
99
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model.bin",
100
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model.bin",
101
+ "model.layers.10.input_layernorm.weight": "pytorch_model.bin",
102
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model.bin",
103
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model.bin",
104
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model.bin",
105
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model.bin",
106
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model.bin",
107
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model.bin",
108
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model.bin",
109
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model.bin",
110
+ "model.layers.11.input_layernorm.weight": "pytorch_model.bin",
111
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model.bin",
112
+ "model.norm.weight": "pytorch_model.bin",
113
+ "lm_head.weight": "pytorch_model.bin"
114
+ },
115
+ "metadata": {
116
+ "total_size": 1072271360
117
+ }
118
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small3+UseDeepSpeed.true+UseExternal.false/tokenizer_config.json ADDED
@@ -0,0 +1,844 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "10": {
20
+ "content": "<extra_id_6>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "100": {
28
+ "content": "<extra_id_96>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "101": {
36
+ "content": "<extra_id_97>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "102": {
44
+ "content": "<extra_id_98>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "103": {
52
+ "content": "<extra_id_99>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "11": {
60
+ "content": "<extra_id_7>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "12": {
68
+ "content": "<extra_id_8>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "13": {
76
+ "content": "<extra_id_9>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "14": {
84
+ "content": "<extra_id_10>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "15": {
92
+ "content": "<extra_id_11>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "16": {
100
+ "content": "<extra_id_12>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "17": {
108
+ "content": "<extra_id_13>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "18": {
116
+ "content": "<extra_id_14>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "19": {
124
+ "content": "<extra_id_15>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "2": {
132
+ "content": "</s>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "20": {
140
+ "content": "<extra_id_16>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "21": {
148
+ "content": "<extra_id_17>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "22": {
156
+ "content": "<extra_id_18>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "23": {
164
+ "content": "<extra_id_19>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "24": {
172
+ "content": "<extra_id_20>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "25": {
180
+ "content": "<extra_id_21>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "26": {
188
+ "content": "<extra_id_22>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "27": {
196
+ "content": "<extra_id_23>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "28": {
204
+ "content": "<extra_id_24>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "29": {
212
+ "content": "<extra_id_25>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "3": {
220
+ "content": "<pad>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "30": {
228
+ "content": "<extra_id_26>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "31": {
236
+ "content": "<extra_id_27>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "32": {
244
+ "content": "<extra_id_28>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "33": {
252
+ "content": "<extra_id_29>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "34": {
260
+ "content": "<extra_id_30>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "35": {
268
+ "content": "<extra_id_31>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "36": {
276
+ "content": "<extra_id_32>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "37": {
284
+ "content": "<extra_id_33>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "38": {
292
+ "content": "<extra_id_34>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "39": {
300
+ "content": "<extra_id_35>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "4": {
308
+ "content": "<extra_id_0>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "40": {
316
+ "content": "<extra_id_36>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "41": {
324
+ "content": "<extra_id_37>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "42": {
332
+ "content": "<extra_id_38>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "43": {
340
+ "content": "<extra_id_39>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "44": {
348
+ "content": "<extra_id_40>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "45": {
356
+ "content": "<extra_id_41>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "46": {
364
+ "content": "<extra_id_42>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "47": {
372
+ "content": "<extra_id_43>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "48": {
380
+ "content": "<extra_id_44>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "49": {
388
+ "content": "<extra_id_45>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "5": {
396
+ "content": "<extra_id_1>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "50": {
404
+ "content": "<extra_id_46>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "51": {
412
+ "content": "<extra_id_47>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "52": {
420
+ "content": "<extra_id_48>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "53": {
428
+ "content": "<extra_id_49>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "54": {
436
+ "content": "<extra_id_50>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "55": {
444
+ "content": "<extra_id_51>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "56": {
452
+ "content": "<extra_id_52>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "57": {
460
+ "content": "<extra_id_53>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "58": {
468
+ "content": "<extra_id_54>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "59": {
476
+ "content": "<extra_id_55>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "6": {
484
+ "content": "<extra_id_2>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "60": {
492
+ "content": "<extra_id_56>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "61": {
500
+ "content": "<extra_id_57>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "62": {
508
+ "content": "<extra_id_58>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "63": {
516
+ "content": "<extra_id_59>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "64": {
524
+ "content": "<extra_id_60>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "65": {
532
+ "content": "<extra_id_61>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "66": {
540
+ "content": "<extra_id_62>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "67": {
548
+ "content": "<extra_id_63>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "68": {
556
+ "content": "<extra_id_64>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "69": {
564
+ "content": "<extra_id_65>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "7": {
572
+ "content": "<extra_id_3>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "70": {
580
+ "content": "<extra_id_66>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "71": {
588
+ "content": "<extra_id_67>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "72": {
596
+ "content": "<extra_id_68>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "73": {
604
+ "content": "<extra_id_69>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "74": {
612
+ "content": "<extra_id_70>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "75": {
620
+ "content": "<extra_id_71>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "76": {
628
+ "content": "<extra_id_72>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "77": {
636
+ "content": "<extra_id_73>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "78": {
644
+ "content": "<extra_id_74>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "79": {
652
+ "content": "<extra_id_75>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "8": {
660
+ "content": "<extra_id_4>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "80": {
668
+ "content": "<extra_id_76>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "81": {
676
+ "content": "<extra_id_77>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "82": {
684
+ "content": "<extra_id_78>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "83": {
692
+ "content": "<extra_id_79>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "84": {
700
+ "content": "<extra_id_80>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "85": {
708
+ "content": "<extra_id_81>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "86": {
716
+ "content": "<extra_id_82>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "87": {
724
+ "content": "<extra_id_83>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "88": {
732
+ "content": "<extra_id_84>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "89": {
740
+ "content": "<extra_id_85>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "9": {
748
+ "content": "<extra_id_5>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "90": {
756
+ "content": "<extra_id_86>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "91": {
764
+ "content": "<extra_id_87>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "92": {
772
+ "content": "<extra_id_88>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "93": {
780
+ "content": "<extra_id_89>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "94": {
788
+ "content": "<extra_id_90>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "95": {
796
+ "content": "<extra_id_91>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "96": {
804
+ "content": "<extra_id_92>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "97": {
812
+ "content": "<extra_id_93>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "98": {
820
+ "content": "<extra_id_94>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "99": {
828
+ "content": "<extra_id_95>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ }
835
+ },
836
+ "additional_special_tokens": [],
837
+ "bos_token": "<s>",
838
+ "clean_up_tokenization_spaces": false,
839
+ "eos_token": "</s>",
840
+ "model_max_length": 1000000000000000019884624838656,
841
+ "tokenizer_class": "LlamaTokenizer",
842
+ "unk_token": "<unk>",
843
+ "use_default_system_prompt": true
844
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 1536,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 4128,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 12,
14
+ "num_hidden_layers": 12,
15
+ "num_key_value_heads": 12,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "rope_theta": 10000.0,
20
+ "tie_word_embeddings": false,
21
+ "transformers_version": "4.33.3",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
DSAutotuneConfig.false+DataMix.equal+Dataset.french+Size.small4+UseDeepSpeed.true+UseExternal.false/hf_model/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "hidden_act": "silu",
8
+ "hidden_size": 1536,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 4128,
11
+ "max_position_embeddings": 2048,
12
+ "model_type": "llama",
13
+ "num_attention_heads": 12,
14
+ "num_hidden_layers": 12,
15
+ "num_key_value_heads": 12,
16
+ "pretraining_tp": 1,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_scaling": null,
19
+ "rope_theta": 10000.0,
20
+ "tie_word_embeddings": false,
21
+ "transformers_version": "4.33.3",
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }