Hugging Face's logo

Saif-M
/
PokeBrain-V2-2.6B

Text Generation
Transformers
Safetensors
gpt_neo
Inference Endpoints
Model card Files Community
Saif-M commited on
Commit
9e0691b
•
1 Parent(s): 857e2ca

Upload 22 files

Browse files
Files changed (22) hide show
  1. checkpoint-500/config.json +83 -0
  2. checkpoint-500/generation_config.json +6 -0
  3. checkpoint-500/model-00001-of-00003.safetensors +3 -0
  4. checkpoint-500/model-00002-of-00003.safetensors +3 -0
  5. checkpoint-500/model-00003-of-00003.safetensors +3 -0
  6. checkpoint-500/model.safetensors.index.json +427 -0
  7. checkpoint-500/optimizer.pt +3 -0
  8. checkpoint-500/rng_state.pth +3 -0
  9. checkpoint-500/scheduler.pt +3 -0
  10. checkpoint-500/trainer_state.json +75 -0
  11. checkpoint-500/training_args.bin +3 -0
  12. config.json +83 -0
  13. generation_config.json +6 -0
  14. merges.txt +0 -0
  15. model-00001-of-00003.safetensors +3 -0
  16. model-00002-of-00003.safetensors +3 -0
  17. model-00003-of-00003.safetensors +3 -0
  18. model.safetensors.index.json +427 -0
  19. special_tokens_map.json +24 -0
  20. tokenizer_config.json +22 -0
  21. training_args.bin +3 -0
  22. vocab.json +0 -0
checkpoint-500/config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-2.7B",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local",
33
+ "global",
34
+ "local",
35
+ "global",
36
+ "local",
37
+ "global",
38
+ "local",
39
+ "global",
40
+ "local"
41
+ ],
42
+ "attention_types": [
43
+ [
44
+ [
45
+ "global",
46
+ "local"
47
+ ],
48
+ 16
49
+ ]
50
+ ],
51
+ "bos_token_id": 50256,
52
+ "classifier_dropout": 0.1,
53
+ "embed_dropout": 0,
54
+ "eos_token_id": 50256,
55
+ "gradient_checkpointing": false,
56
+ "hidden_size": 2560,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": null,
59
+ "layer_norm_epsilon": 1e-05,
60
+ "max_position_embeddings": 2048,
61
+ "model_type": "gpt_neo",
62
+ "num_heads": 20,
63
+ "num_layers": 32,
64
+ "resid_dropout": 0,
65
+ "summary_activation": null,
66
+ "summary_first_dropout": 0.1,
67
+ "summary_proj_to_labels": true,
68
+ "summary_type": "cls_index",
69
+ "summary_use_proj": true,
70
+ "task_specific_params": {
71
+ "text-generation": {
72
+ "do_sample": true,
73
+ "max_length": 50,
74
+ "temperature": 0.9
75
+ }
76
+ },
77
+ "tokenizer_class": "GPT2Tokenizer",
78
+ "torch_dtype": "float32",
79
+ "transformers_version": "4.41.2",
80
+ "use_cache": true,
81
+ "vocab_size": 50257,
82
+ "window_size": 256
83
+ }
checkpoint-500/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.41.2"
6
+ }
checkpoint-500/model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f57419d1a5cdd2ee8e311c9c1b560d8f0e20088d8cb790e24f580b4bc00f469
3
+ size 4993525968
checkpoint-500/model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52df8f421dd4e3ce74c7304b669816c2c9c457229e00993d556d31b3d173e619
3
+ size 4982397200
checkpoint-500/model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9f91e9abaa746ff4b714e4391410f2906f2d073f511f9c5d52d5378ada7989
3
+ size 629353256
checkpoint-500/model.safetensors.index.json ADDED
@@ -0,0 +1,427 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 10605230080
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
7
+ "transformer.h.0.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
8
+ "transformer.h.0.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
9
+ "transformer.h.0.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
10
+ "transformer.h.0.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
11
+ "transformer.h.0.ln_1.bias": "model-00001-of-00003.safetensors",
12
+ "transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
13
+ "transformer.h.0.ln_2.bias": "model-00001-of-00003.safetensors",
14
+ "transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
15
+ "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
16
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
17
+ "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
18
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
19
+ "transformer.h.1.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
20
+ "transformer.h.1.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
21
+ "transformer.h.1.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
22
+ "transformer.h.1.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
23
+ "transformer.h.1.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
24
+ "transformer.h.1.ln_1.bias": "model-00001-of-00003.safetensors",
25
+ "transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
26
+ "transformer.h.1.ln_2.bias": "model-00001-of-00003.safetensors",
27
+ "transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
28
+ "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
29
+ "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
30
+ "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
31
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
32
+ "transformer.h.10.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
33
+ "transformer.h.10.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
34
+ "transformer.h.10.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
35
+ "transformer.h.10.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
36
+ "transformer.h.10.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
37
+ "transformer.h.10.ln_1.bias": "model-00001-of-00003.safetensors",
38
+ "transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors",
39
+ "transformer.h.10.ln_2.bias": "model-00001-of-00003.safetensors",
40
+ "transformer.h.10.ln_2.weight": "model-00001-of-00003.safetensors",
41
+ "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
42
+ "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
43
+ "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
44
+ "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
45
+ "transformer.h.11.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
46
+ "transformer.h.11.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
47
+ "transformer.h.11.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
48
+ "transformer.h.11.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
49
+ "transformer.h.11.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
50
+ "transformer.h.11.ln_1.bias": "model-00001-of-00003.safetensors",
51
+ "transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
52
+ "transformer.h.11.ln_2.bias": "model-00001-of-00003.safetensors",
53
+ "transformer.h.11.ln_2.weight": "model-00001-of-00003.safetensors",
54
+ "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
55
+ "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
56
+ "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
57
+ "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
58
+ "transformer.h.12.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
59
+ "transformer.h.12.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
60
+ "transformer.h.12.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
61
+ "transformer.h.12.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
62
+ "transformer.h.12.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
63
+ "transformer.h.12.ln_1.bias": "model-00001-of-00003.safetensors",
64
+ "transformer.h.12.ln_1.weight": "model-00001-of-00003.safetensors",
65
+ "transformer.h.12.ln_2.bias": "model-00001-of-00003.safetensors",
66
+ "transformer.h.12.ln_2.weight": "model-00001-of-00003.safetensors",
67
+ "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
68
+ "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
69
+ "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
70
+ "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
71
+ "transformer.h.13.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
72
+ "transformer.h.13.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
73
+ "transformer.h.13.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
74
+ "transformer.h.13.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
75
+ "transformer.h.13.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
76
+ "transformer.h.13.ln_1.bias": "model-00001-of-00003.safetensors",
77
+ "transformer.h.13.ln_1.weight": "model-00001-of-00003.safetensors",
78
+ "transformer.h.13.ln_2.bias": "model-00001-of-00003.safetensors",
79
+ "transformer.h.13.ln_2.weight": "model-00001-of-00003.safetensors",
80
+ "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
81
+ "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
82
+ "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
83
+ "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
84
+ "transformer.h.14.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
85
+ "transformer.h.14.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
86
+ "transformer.h.14.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
87
+ "transformer.h.14.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "transformer.h.14.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
89
+ "transformer.h.14.ln_1.bias": "model-00001-of-00003.safetensors",
90
+ "transformer.h.14.ln_1.weight": "model-00001-of-00003.safetensors",
91
+ "transformer.h.14.ln_2.bias": "model-00002-of-00003.safetensors",
92
+ "transformer.h.14.ln_2.weight": "model-00002-of-00003.safetensors",
93
+ "transformer.h.14.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
94
+ "transformer.h.14.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
95
+ "transformer.h.14.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
96
+ "transformer.h.14.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
97
+ "transformer.h.15.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
98
+ "transformer.h.15.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
99
+ "transformer.h.15.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
100
+ "transformer.h.15.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
101
+ "transformer.h.15.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
102
+ "transformer.h.15.ln_1.bias": "model-00002-of-00003.safetensors",
103
+ "transformer.h.15.ln_1.weight": "model-00002-of-00003.safetensors",
104
+ "transformer.h.15.ln_2.bias": "model-00002-of-00003.safetensors",
105
+ "transformer.h.15.ln_2.weight": "model-00002-of-00003.safetensors",
106
+ "transformer.h.15.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
107
+ "transformer.h.15.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
108
+ "transformer.h.15.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
109
+ "transformer.h.15.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
110
+ "transformer.h.16.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
111
+ "transformer.h.16.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
112
+ "transformer.h.16.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
113
+ "transformer.h.16.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
114
+ "transformer.h.16.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
115
+ "transformer.h.16.ln_1.bias": "model-00002-of-00003.safetensors",
116
+ "transformer.h.16.ln_1.weight": "model-00002-of-00003.safetensors",
117
+ "transformer.h.16.ln_2.bias": "model-00002-of-00003.safetensors",
118
+ "transformer.h.16.ln_2.weight": "model-00002-of-00003.safetensors",
119
+ "transformer.h.16.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
120
+ "transformer.h.16.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
121
+ "transformer.h.16.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
122
+ "transformer.h.16.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
123
+ "transformer.h.17.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
124
+ "transformer.h.17.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
125
+ "transformer.h.17.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
126
+ "transformer.h.17.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
127
+ "transformer.h.17.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
128
+ "transformer.h.17.ln_1.bias": "model-00002-of-00003.safetensors",
129
+ "transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
130
+ "transformer.h.17.ln_2.bias": "model-00002-of-00003.safetensors",
131
+ "transformer.h.17.ln_2.weight": "model-00002-of-00003.safetensors",
132
+ "transformer.h.17.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
133
+ "transformer.h.17.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
134
+ "transformer.h.17.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
135
+ "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
136
+ "transformer.h.18.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
137
+ "transformer.h.18.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
138
+ "transformer.h.18.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
139
+ "transformer.h.18.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
140
+ "transformer.h.18.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
141
+ "transformer.h.18.ln_1.bias": "model-00002-of-00003.safetensors",
142
+ "transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
143
+ "transformer.h.18.ln_2.bias": "model-00002-of-00003.safetensors",
144
+ "transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors",
145
+ "transformer.h.18.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
146
+ "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
147
+ "transformer.h.18.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
148
+ "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
149
+ "transformer.h.19.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
150
+ "transformer.h.19.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
151
+ "transformer.h.19.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
152
+ "transformer.h.19.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
153
+ "transformer.h.19.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
154
+ "transformer.h.19.ln_1.bias": "model-00002-of-00003.safetensors",
155
+ "transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors",
156
+ "transformer.h.19.ln_2.bias": "model-00002-of-00003.safetensors",
157
+ "transformer.h.19.ln_2.weight": "model-00002-of-00003.safetensors",
158
+ "transformer.h.19.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
159
+ "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
160
+ "transformer.h.19.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
161
+ "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
162
+ "transformer.h.2.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
163
+ "transformer.h.2.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
164
+ "transformer.h.2.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
165
+ "transformer.h.2.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
166
+ "transformer.h.2.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
167
+ "transformer.h.2.ln_1.bias": "model-00001-of-00003.safetensors",
168
+ "transformer.h.2.ln_1.weight": "model-00001-of-00003.safetensors",
169
+ "transformer.h.2.ln_2.bias": "model-00001-of-00003.safetensors",
170
+ "transformer.h.2.ln_2.weight": "model-00001-of-00003.safetensors",
171
+ "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
172
+ "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
173
+ "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
174
+ "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
175
+ "transformer.h.20.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
176
+ "transformer.h.20.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
177
+ "transformer.h.20.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
178
+ "transformer.h.20.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
179
+ "transformer.h.20.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
180
+ "transformer.h.20.ln_1.bias": "model-00002-of-00003.safetensors",
181
+ "transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
182
+ "transformer.h.20.ln_2.bias": "model-00002-of-00003.safetensors",
183
+ "transformer.h.20.ln_2.weight": "model-00002-of-00003.safetensors",
184
+ "transformer.h.20.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
185
+ "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
186
+ "transformer.h.20.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
187
+ "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
188
+ "transformer.h.21.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
189
+ "transformer.h.21.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
190
+ "transformer.h.21.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
191
+ "transformer.h.21.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
192
+ "transformer.h.21.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
193
+ "transformer.h.21.ln_1.bias": "model-00002-of-00003.safetensors",
194
+ "transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
195
+ "transformer.h.21.ln_2.bias": "model-00002-of-00003.safetensors",
196
+ "transformer.h.21.ln_2.weight": "model-00002-of-00003.safetensors",
197
+ "transformer.h.21.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
198
+ "transformer.h.21.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
199
+ "transformer.h.21.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
200
+ "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
201
+ "transformer.h.22.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
202
+ "transformer.h.22.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
203
+ "transformer.h.22.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
204
+ "transformer.h.22.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
205
+ "transformer.h.22.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
206
+ "transformer.h.22.ln_1.bias": "model-00002-of-00003.safetensors",
207
+ "transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors",
208
+ "transformer.h.22.ln_2.bias": "model-00002-of-00003.safetensors",
209
+ "transformer.h.22.ln_2.weight": "model-00002-of-00003.safetensors",
210
+ "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
211
+ "transformer.h.22.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
212
+ "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
213
+ "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
214
+ "transformer.h.23.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
215
+ "transformer.h.23.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
216
+ "transformer.h.23.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
217
+ "transformer.h.23.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
218
+ "transformer.h.23.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
219
+ "transformer.h.23.ln_1.bias": "model-00002-of-00003.safetensors",
220
+ "transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
221
+ "transformer.h.23.ln_2.bias": "model-00002-of-00003.safetensors",
222
+ "transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors",
223
+ "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
224
+ "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
225
+ "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
226
+ "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
227
+ "transformer.h.24.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
228
+ "transformer.h.24.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
229
+ "transformer.h.24.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
230
+ "transformer.h.24.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
231
+ "transformer.h.24.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
232
+ "transformer.h.24.ln_1.bias": "model-00002-of-00003.safetensors",
233
+ "transformer.h.24.ln_1.weight": "model-00002-of-00003.safetensors",
234
+ "transformer.h.24.ln_2.bias": "model-00002-of-00003.safetensors",
235
+ "transformer.h.24.ln_2.weight": "model-00002-of-00003.safetensors",
236
+ "transformer.h.24.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
237
+ "transformer.h.24.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
238
+ "transformer.h.24.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
239
+ "transformer.h.24.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
240
+ "transformer.h.25.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
241
+ "transformer.h.25.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
242
+ "transformer.h.25.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
243
+ "transformer.h.25.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
244
+ "transformer.h.25.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
245
+ "transformer.h.25.ln_1.bias": "model-00002-of-00003.safetensors",
246
+ "transformer.h.25.ln_1.weight": "model-00002-of-00003.safetensors",
247
+ "transformer.h.25.ln_2.bias": "model-00002-of-00003.safetensors",
248
+ "transformer.h.25.ln_2.weight": "model-00002-of-00003.safetensors",
249
+ "transformer.h.25.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
250
+ "transformer.h.25.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
251
+ "transformer.h.25.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
252
+ "transformer.h.25.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
253
+ "transformer.h.26.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
254
+ "transformer.h.26.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
255
+ "transformer.h.26.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
256
+ "transformer.h.26.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
257
+ "transformer.h.26.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
258
+ "transformer.h.26.ln_1.bias": "model-00002-of-00003.safetensors",
259
+ "transformer.h.26.ln_1.weight": "model-00002-of-00003.safetensors",
260
+ "transformer.h.26.ln_2.bias": "model-00002-of-00003.safetensors",
261
+ "transformer.h.26.ln_2.weight": "model-00002-of-00003.safetensors",
262
+ "transformer.h.26.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
263
+ "transformer.h.26.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
264
+ "transformer.h.26.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
265
+ "transformer.h.26.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
266
+ "transformer.h.27.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
267
+ "transformer.h.27.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
268
+ "transformer.h.27.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
269
+ "transformer.h.27.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
270
+ "transformer.h.27.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
271
+ "transformer.h.27.ln_1.bias": "model-00002-of-00003.safetensors",
272
+ "transformer.h.27.ln_1.weight": "model-00002-of-00003.safetensors",
273
+ "transformer.h.27.ln_2.bias": "model-00002-of-00003.safetensors",
274
+ "transformer.h.27.ln_2.weight": "model-00002-of-00003.safetensors",
275
+ "transformer.h.27.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
276
+ "transformer.h.27.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
277
+ "transformer.h.27.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
278
+ "transformer.h.27.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
279
+ "transformer.h.28.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
280
+ "transformer.h.28.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
281
+ "transformer.h.28.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
282
+ "transformer.h.28.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
283
+ "transformer.h.28.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
284
+ "transformer.h.28.ln_1.bias": "model-00002-of-00003.safetensors",
285
+ "transformer.h.28.ln_1.weight": "model-00002-of-00003.safetensors",
286
+ "transformer.h.28.ln_2.bias": "model-00002-of-00003.safetensors",
287
+ "transformer.h.28.ln_2.weight": "model-00002-of-00003.safetensors",
288
+ "transformer.h.28.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
289
+ "transformer.h.28.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
290
+ "transformer.h.28.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
291
+ "transformer.h.28.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
292
+ "transformer.h.29.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
293
+ "transformer.h.29.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
294
+ "transformer.h.29.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
295
+ "transformer.h.29.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
296
+ "transformer.h.29.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
297
+ "transformer.h.29.ln_1.bias": "model-00002-of-00003.safetensors",
298
+ "transformer.h.29.ln_1.weight": "model-00002-of-00003.safetensors",
299
+ "transformer.h.29.ln_2.bias": "model-00002-of-00003.safetensors",
300
+ "transformer.h.29.ln_2.weight": "model-00002-of-00003.safetensors",
301
+ "transformer.h.29.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
302
+ "transformer.h.29.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
303
+ "transformer.h.29.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
304
+ "transformer.h.29.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
305
+ "transformer.h.3.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
306
+ "transformer.h.3.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
307
+ "transformer.h.3.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
308
+ "transformer.h.3.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
309
+ "transformer.h.3.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
310
+ "transformer.h.3.ln_1.bias": "model-00001-of-00003.safetensors",
311
+ "transformer.h.3.ln_1.weight": "model-00001-of-00003.safetensors",
312
+ "transformer.h.3.ln_2.bias": "model-00001-of-00003.safetensors",
313
+ "transformer.h.3.ln_2.weight": "model-00001-of-00003.safetensors",
314
+ "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
315
+ "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
316
+ "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
317
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
318
+ "transformer.h.30.attn.attention.k_proj.weight": "model-00003-of-00003.safetensors",
319
+ "transformer.h.30.attn.attention.out_proj.bias": "model-00003-of-00003.safetensors",
320
+ "transformer.h.30.attn.attention.out_proj.weight": "model-00003-of-00003.safetensors",
321
+ "transformer.h.30.attn.attention.q_proj.weight": "model-00003-of-00003.safetensors",
322
+ "transformer.h.30.attn.attention.v_proj.weight": "model-00003-of-00003.safetensors",
323
+ "transformer.h.30.ln_1.bias": "model-00002-of-00003.safetensors",
324
+ "transformer.h.30.ln_1.weight": "model-00002-of-00003.safetensors",
325
+ "transformer.h.30.ln_2.bias": "model-00003-of-00003.safetensors",
326
+ "transformer.h.30.ln_2.weight": "model-00003-of-00003.safetensors",
327
+ "transformer.h.30.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
328
+ "transformer.h.30.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
329
+ "transformer.h.30.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
330
+ "transformer.h.30.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
331
+ "transformer.h.31.attn.attention.k_proj.weight": "model-00003-of-00003.safetensors",
332
+ "transformer.h.31.attn.attention.out_proj.bias": "model-00003-of-00003.safetensors",
333
+ "transformer.h.31.attn.attention.out_proj.weight": "model-00003-of-00003.safetensors",
334
+ "transformer.h.31.attn.attention.q_proj.weight": "model-00003-of-00003.safetensors",
335
+ "transformer.h.31.attn.attention.v_proj.weight": "model-00003-of-00003.safetensors",
336
+ "transformer.h.31.ln_1.bias": "model-00003-of-00003.safetensors",
337
+ "transformer.h.31.ln_1.weight": "model-00003-of-00003.safetensors",
338
+ "transformer.h.31.ln_2.bias": "model-00003-of-00003.safetensors",
339
+ "transformer.h.31.ln_2.weight": "model-00003-of-00003.safetensors",
340
+ "transformer.h.31.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
341
+ "transformer.h.31.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
342
+ "transformer.h.31.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
343
+ "transformer.h.31.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
344
+ "transformer.h.4.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
345
+ "transformer.h.4.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
346
+ "transformer.h.4.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
347
+ "transformer.h.4.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
348
+ "transformer.h.4.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
349
+ "transformer.h.4.ln_1.bias": "model-00001-of-00003.safetensors",
350
+ "transformer.h.4.ln_1.weight": "model-00001-of-00003.safetensors",
351
+ "transformer.h.4.ln_2.bias": "model-00001-of-00003.safetensors",
352
+ "transformer.h.4.ln_2.weight": "model-00001-of-00003.safetensors",
353
+ "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
354
+ "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
355
+ "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
356
+ "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
357
+ "transformer.h.5.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
358
+ "transformer.h.5.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
359
+ "transformer.h.5.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
360
+ "transformer.h.5.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
361
+ "transformer.h.5.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
362
+ "transformer.h.5.ln_1.bias": "model-00001-of-00003.safetensors",
363
+ "transformer.h.5.ln_1.weight": "model-00001-of-00003.safetensors",
364
+ "transformer.h.5.ln_2.bias": "model-00001-of-00003.safetensors",
365
+ "transformer.h.5.ln_2.weight": "model-00001-of-00003.safetensors",
366
+ "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
367
+ "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
368
+ "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
369
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
370
+ "transformer.h.6.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
371
+ "transformer.h.6.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
372
+ "transformer.h.6.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
373
+ "transformer.h.6.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
374
+ "transformer.h.6.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
375
+ "transformer.h.6.ln_1.bias": "model-00001-of-00003.safetensors",
376
+ "transformer.h.6.ln_1.weight": "model-00001-of-00003.safetensors",
377
+ "transformer.h.6.ln_2.bias": "model-00001-of-00003.safetensors",
378
+ "transformer.h.6.ln_2.weight": "model-00001-of-00003.safetensors",
379
+ "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
380
+ "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
381
+ "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
382
+ "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
383
+ "transformer.h.7.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
384
+ "transformer.h.7.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
385
+ "transformer.h.7.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
386
+ "transformer.h.7.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
387
+ "transformer.h.7.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
388
+ "transformer.h.7.ln_1.bias": "model-00001-of-00003.safetensors",
389
+ "transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
390
+ "transformer.h.7.ln_2.bias": "model-00001-of-00003.safetensors",
391
+ "transformer.h.7.ln_2.weight": "model-00001-of-00003.safetensors",
392
+ "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
393
+ "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
394
+ "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
395
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
396
+ "transformer.h.8.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
397
+ "transformer.h.8.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
398
+ "transformer.h.8.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
399
+ "transformer.h.8.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
400
+ "transformer.h.8.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
401
+ "transformer.h.8.ln_1.bias": "model-00001-of-00003.safetensors",
402
+ "transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
403
+ "transformer.h.8.ln_2.bias": "model-00001-of-00003.safetensors",
404
+ "transformer.h.8.ln_2.weight": "model-00001-of-00003.safetensors",
405
+ "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
406
+ "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
407
+ "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
408
+ "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
409
+ "transformer.h.9.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
410
+ "transformer.h.9.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
411
+ "transformer.h.9.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
412
+ "transformer.h.9.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
413
+ "transformer.h.9.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
414
+ "transformer.h.9.ln_1.bias": "model-00001-of-00003.safetensors",
415
+ "transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
416
+ "transformer.h.9.ln_2.bias": "model-00001-of-00003.safetensors",
417
+ "transformer.h.9.ln_2.weight": "model-00001-of-00003.safetensors",
418
+ "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
419
+ "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
420
+ "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
421
+ "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
422
+ "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
423
+ "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
424
+ "transformer.wpe.weight": "model-00001-of-00003.safetensors",
425
+ "transformer.wte.weight": "model-00001-of-00003.safetensors"
426
+ }
427
+ }
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db398e54db4e91062be6a28b436ab4b4bfaee0959f6a9ff5a9dcbb20d48b43c
3
+ size 21210811314
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06e55bfc8723f269a626afca0be6f7def5753f3bb265436b94c5580b703cfcc7
3
+ size 13990
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e459471b8677f1f763290496f00cfaf88c250cecded98454d7952c34ad3a070d
3
+ size 1064
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.2894736842105265,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.006578947368421052,
13
+ "grad_norm": 61.44523239135742,
14
+ "learning_rate": 4.9934210526315795e-05,
15
+ "loss": 5.7871,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.6578947368421053,
20
+ "grad_norm": NaN,
21
+ "learning_rate": 4.342105263157895e-05,
22
+ "loss": 0.0,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 1.3157894736842106,
27
+ "grad_norm": NaN,
28
+ "learning_rate": 3.6842105263157895e-05,
29
+ "loss": 0.0,
30
+ "step": 200
31
+ },
32
+ {
33
+ "epoch": 1.973684210526316,
34
+ "grad_norm": NaN,
35
+ "learning_rate": 3.0263157894736844e-05,
36
+ "loss": 0.0,
37
+ "step": 300
38
+ },
39
+ {
40
+ "epoch": 2.6315789473684212,
41
+ "grad_norm": NaN,
42
+ "learning_rate": 2.368421052631579e-05,
43
+ "loss": 0.0,
44
+ "step": 400
45
+ },
46
+ {
47
+ "epoch": 3.2894736842105265,
48
+ "grad_norm": NaN,
49
+ "learning_rate": 1.7105263157894737e-05,
50
+ "loss": 0.0,
51
+ "step": 500
52
+ }
53
+ ],
54
+ "logging_steps": 100,
55
+ "max_steps": 760,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 5,
58
+ "save_steps": 500,
59
+ "stateful_callbacks": {
60
+ "TrainerControl": {
61
+ "args": {
62
+ "should_epoch_stop": false,
63
+ "should_evaluate": false,
64
+ "should_log": false,
65
+ "should_save": true,
66
+ "should_training_stop": false
67
+ },
68
+ "attributes": {}
69
+ }
70
+ },
71
+ "total_flos": 7727673338757120.0,
72
+ "train_batch_size": 2,
73
+ "trial_name": null,
74
+ "trial_params": null
75
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a330312962b0a11f240598dd20275d49f2b3457046e0c713045d6647d014f1
3
+ size 4984
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-2.7B",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local",
33
+ "global",
34
+ "local",
35
+ "global",
36
+ "local",
37
+ "global",
38
+ "local",
39
+ "global",
40
+ "local"
41
+ ],
42
+ "attention_types": [
43
+ [
44
+ [
45
+ "global",
46
+ "local"
47
+ ],
48
+ 16
49
+ ]
50
+ ],
51
+ "bos_token_id": 50256,
52
+ "classifier_dropout": 0.1,
53
+ "embed_dropout": 0,
54
+ "eos_token_id": 50256,
55
+ "gradient_checkpointing": false,
56
+ "hidden_size": 2560,
57
+ "initializer_range": 0.02,
58
+ "intermediate_size": null,
59
+ "layer_norm_epsilon": 1e-05,
60
+ "max_position_embeddings": 2048,
61
+ "model_type": "gpt_neo",
62
+ "num_heads": 20,
63
+ "num_layers": 32,
64
+ "resid_dropout": 0,
65
+ "summary_activation": null,
66
+ "summary_first_dropout": 0.1,
67
+ "summary_proj_to_labels": true,
68
+ "summary_type": "cls_index",
69
+ "summary_use_proj": true,
70
+ "task_specific_params": {
71
+ "text-generation": {
72
+ "do_sample": true,
73
+ "max_length": 50,
74
+ "temperature": 0.9
75
+ }
76
+ },
77
+ "tokenizer_class": "GPT2Tokenizer",
78
+ "torch_dtype": "float32",
79
+ "transformers_version": "4.41.2",
80
+ "use_cache": true,
81
+ "vocab_size": 50257,
82
+ "window_size": 256
83
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.41.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f57419d1a5cdd2ee8e311c9c1b560d8f0e20088d8cb790e24f580b4bc00f469
3
+ size 4993525968
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52df8f421dd4e3ce74c7304b669816c2c9c457229e00993d556d31b3d173e619
3
+ size 4982397200
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9f91e9abaa746ff4b714e4391410f2906f2d073f511f9c5d52d5378ada7989
3
+ size 629353256
model.safetensors.index.json ADDED
@@ -0,0 +1,427 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 10605230080
4
+ },
5
+ "weight_map": {
6
+ "transformer.h.0.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
7
+ "transformer.h.0.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
8
+ "transformer.h.0.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
9
+ "transformer.h.0.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
10
+ "transformer.h.0.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
11
+ "transformer.h.0.ln_1.bias": "model-00001-of-00003.safetensors",
12
+ "transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
13
+ "transformer.h.0.ln_2.bias": "model-00001-of-00003.safetensors",
14
+ "transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
15
+ "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
16
+ "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
17
+ "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
18
+ "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
19
+ "transformer.h.1.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
20
+ "transformer.h.1.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
21
+ "transformer.h.1.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
22
+ "transformer.h.1.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
23
+ "transformer.h.1.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
24
+ "transformer.h.1.ln_1.bias": "model-00001-of-00003.safetensors",
25
+ "transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
26
+ "transformer.h.1.ln_2.bias": "model-00001-of-00003.safetensors",
27
+ "transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
28
+ "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
29
+ "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
30
+ "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
31
+ "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
32
+ "transformer.h.10.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
33
+ "transformer.h.10.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
34
+ "transformer.h.10.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
35
+ "transformer.h.10.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
36
+ "transformer.h.10.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
37
+ "transformer.h.10.ln_1.bias": "model-00001-of-00003.safetensors",
38
+ "transformer.h.10.ln_1.weight": "model-00001-of-00003.safetensors",
39
+ "transformer.h.10.ln_2.bias": "model-00001-of-00003.safetensors",
40
+ "transformer.h.10.ln_2.weight": "model-00001-of-00003.safetensors",
41
+ "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
42
+ "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
43
+ "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
44
+ "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
45
+ "transformer.h.11.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
46
+ "transformer.h.11.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
47
+ "transformer.h.11.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
48
+ "transformer.h.11.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
49
+ "transformer.h.11.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
50
+ "transformer.h.11.ln_1.bias": "model-00001-of-00003.safetensors",
51
+ "transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
52
+ "transformer.h.11.ln_2.bias": "model-00001-of-00003.safetensors",
53
+ "transformer.h.11.ln_2.weight": "model-00001-of-00003.safetensors",
54
+ "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
55
+ "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
56
+ "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
57
+ "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
58
+ "transformer.h.12.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
59
+ "transformer.h.12.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
60
+ "transformer.h.12.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
61
+ "transformer.h.12.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
62
+ "transformer.h.12.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
63
+ "transformer.h.12.ln_1.bias": "model-00001-of-00003.safetensors",
64
+ "transformer.h.12.ln_1.weight": "model-00001-of-00003.safetensors",
65
+ "transformer.h.12.ln_2.bias": "model-00001-of-00003.safetensors",
66
+ "transformer.h.12.ln_2.weight": "model-00001-of-00003.safetensors",
67
+ "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
68
+ "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
69
+ "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
70
+ "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
71
+ "transformer.h.13.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
72
+ "transformer.h.13.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
73
+ "transformer.h.13.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
74
+ "transformer.h.13.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
75
+ "transformer.h.13.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
76
+ "transformer.h.13.ln_1.bias": "model-00001-of-00003.safetensors",
77
+ "transformer.h.13.ln_1.weight": "model-00001-of-00003.safetensors",
78
+ "transformer.h.13.ln_2.bias": "model-00001-of-00003.safetensors",
79
+ "transformer.h.13.ln_2.weight": "model-00001-of-00003.safetensors",
80
+ "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
81
+ "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
82
+ "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
83
+ "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
84
+ "transformer.h.14.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
85
+ "transformer.h.14.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
86
+ "transformer.h.14.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
87
+ "transformer.h.14.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "transformer.h.14.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
89
+ "transformer.h.14.ln_1.bias": "model-00001-of-00003.safetensors",
90
+ "transformer.h.14.ln_1.weight": "model-00001-of-00003.safetensors",
91
+ "transformer.h.14.ln_2.bias": "model-00002-of-00003.safetensors",
92
+ "transformer.h.14.ln_2.weight": "model-00002-of-00003.safetensors",
93
+ "transformer.h.14.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
94
+ "transformer.h.14.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
95
+ "transformer.h.14.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
96
+ "transformer.h.14.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
97
+ "transformer.h.15.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
98
+ "transformer.h.15.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
99
+ "transformer.h.15.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
100
+ "transformer.h.15.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
101
+ "transformer.h.15.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
102
+ "transformer.h.15.ln_1.bias": "model-00002-of-00003.safetensors",
103
+ "transformer.h.15.ln_1.weight": "model-00002-of-00003.safetensors",
104
+ "transformer.h.15.ln_2.bias": "model-00002-of-00003.safetensors",
105
+ "transformer.h.15.ln_2.weight": "model-00002-of-00003.safetensors",
106
+ "transformer.h.15.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
107
+ "transformer.h.15.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
108
+ "transformer.h.15.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
109
+ "transformer.h.15.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
110
+ "transformer.h.16.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
111
+ "transformer.h.16.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
112
+ "transformer.h.16.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
113
+ "transformer.h.16.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
114
+ "transformer.h.16.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
115
+ "transformer.h.16.ln_1.bias": "model-00002-of-00003.safetensors",
116
+ "transformer.h.16.ln_1.weight": "model-00002-of-00003.safetensors",
117
+ "transformer.h.16.ln_2.bias": "model-00002-of-00003.safetensors",
118
+ "transformer.h.16.ln_2.weight": "model-00002-of-00003.safetensors",
119
+ "transformer.h.16.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
120
+ "transformer.h.16.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
121
+ "transformer.h.16.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
122
+ "transformer.h.16.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
123
+ "transformer.h.17.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
124
+ "transformer.h.17.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
125
+ "transformer.h.17.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
126
+ "transformer.h.17.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
127
+ "transformer.h.17.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
128
+ "transformer.h.17.ln_1.bias": "model-00002-of-00003.safetensors",
129
+ "transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
130
+ "transformer.h.17.ln_2.bias": "model-00002-of-00003.safetensors",
131
+ "transformer.h.17.ln_2.weight": "model-00002-of-00003.safetensors",
132
+ "transformer.h.17.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
133
+ "transformer.h.17.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
134
+ "transformer.h.17.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
135
+ "transformer.h.17.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
136
+ "transformer.h.18.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
137
+ "transformer.h.18.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
138
+ "transformer.h.18.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
139
+ "transformer.h.18.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
140
+ "transformer.h.18.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
141
+ "transformer.h.18.ln_1.bias": "model-00002-of-00003.safetensors",
142
+ "transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
143
+ "transformer.h.18.ln_2.bias": "model-00002-of-00003.safetensors",
144
+ "transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors",
145
+ "transformer.h.18.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
146
+ "transformer.h.18.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
147
+ "transformer.h.18.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
148
+ "transformer.h.18.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
149
+ "transformer.h.19.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
150
+ "transformer.h.19.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
151
+ "transformer.h.19.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
152
+ "transformer.h.19.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
153
+ "transformer.h.19.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
154
+ "transformer.h.19.ln_1.bias": "model-00002-of-00003.safetensors",
155
+ "transformer.h.19.ln_1.weight": "model-00002-of-00003.safetensors",
156
+ "transformer.h.19.ln_2.bias": "model-00002-of-00003.safetensors",
157
+ "transformer.h.19.ln_2.weight": "model-00002-of-00003.safetensors",
158
+ "transformer.h.19.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
159
+ "transformer.h.19.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
160
+ "transformer.h.19.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
161
+ "transformer.h.19.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
162
+ "transformer.h.2.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
163
+ "transformer.h.2.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
164
+ "transformer.h.2.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
165
+ "transformer.h.2.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
166
+ "transformer.h.2.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
167
+ "transformer.h.2.ln_1.bias": "model-00001-of-00003.safetensors",
168
+ "transformer.h.2.ln_1.weight": "model-00001-of-00003.safetensors",
169
+ "transformer.h.2.ln_2.bias": "model-00001-of-00003.safetensors",
170
+ "transformer.h.2.ln_2.weight": "model-00001-of-00003.safetensors",
171
+ "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
172
+ "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
173
+ "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
174
+ "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
175
+ "transformer.h.20.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
176
+ "transformer.h.20.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
177
+ "transformer.h.20.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
178
+ "transformer.h.20.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
179
+ "transformer.h.20.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
180
+ "transformer.h.20.ln_1.bias": "model-00002-of-00003.safetensors",
181
+ "transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
182
+ "transformer.h.20.ln_2.bias": "model-00002-of-00003.safetensors",
183
+ "transformer.h.20.ln_2.weight": "model-00002-of-00003.safetensors",
184
+ "transformer.h.20.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
185
+ "transformer.h.20.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
186
+ "transformer.h.20.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
187
+ "transformer.h.20.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
188
+ "transformer.h.21.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
189
+ "transformer.h.21.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
190
+ "transformer.h.21.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
191
+ "transformer.h.21.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
192
+ "transformer.h.21.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
193
+ "transformer.h.21.ln_1.bias": "model-00002-of-00003.safetensors",
194
+ "transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
195
+ "transformer.h.21.ln_2.bias": "model-00002-of-00003.safetensors",
196
+ "transformer.h.21.ln_2.weight": "model-00002-of-00003.safetensors",
197
+ "transformer.h.21.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
198
+ "transformer.h.21.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
199
+ "transformer.h.21.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
200
+ "transformer.h.21.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
201
+ "transformer.h.22.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
202
+ "transformer.h.22.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
203
+ "transformer.h.22.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
204
+ "transformer.h.22.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
205
+ "transformer.h.22.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
206
+ "transformer.h.22.ln_1.bias": "model-00002-of-00003.safetensors",
207
+ "transformer.h.22.ln_1.weight": "model-00002-of-00003.safetensors",
208
+ "transformer.h.22.ln_2.bias": "model-00002-of-00003.safetensors",
209
+ "transformer.h.22.ln_2.weight": "model-00002-of-00003.safetensors",
210
+ "transformer.h.22.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
211
+ "transformer.h.22.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
212
+ "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
213
+ "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
214
+ "transformer.h.23.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
215
+ "transformer.h.23.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
216
+ "transformer.h.23.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
217
+ "transformer.h.23.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
218
+ "transformer.h.23.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
219
+ "transformer.h.23.ln_1.bias": "model-00002-of-00003.safetensors",
220
+ "transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
221
+ "transformer.h.23.ln_2.bias": "model-00002-of-00003.safetensors",
222
+ "transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors",
223
+ "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
224
+ "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
225
+ "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
226
+ "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
227
+ "transformer.h.24.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
228
+ "transformer.h.24.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
229
+ "transformer.h.24.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
230
+ "transformer.h.24.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
231
+ "transformer.h.24.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
232
+ "transformer.h.24.ln_1.bias": "model-00002-of-00003.safetensors",
233
+ "transformer.h.24.ln_1.weight": "model-00002-of-00003.safetensors",
234
+ "transformer.h.24.ln_2.bias": "model-00002-of-00003.safetensors",
235
+ "transformer.h.24.ln_2.weight": "model-00002-of-00003.safetensors",
236
+ "transformer.h.24.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
237
+ "transformer.h.24.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
238
+ "transformer.h.24.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
239
+ "transformer.h.24.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
240
+ "transformer.h.25.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
241
+ "transformer.h.25.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
242
+ "transformer.h.25.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
243
+ "transformer.h.25.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
244
+ "transformer.h.25.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
245
+ "transformer.h.25.ln_1.bias": "model-00002-of-00003.safetensors",
246
+ "transformer.h.25.ln_1.weight": "model-00002-of-00003.safetensors",
247
+ "transformer.h.25.ln_2.bias": "model-00002-of-00003.safetensors",
248
+ "transformer.h.25.ln_2.weight": "model-00002-of-00003.safetensors",
249
+ "transformer.h.25.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
250
+ "transformer.h.25.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
251
+ "transformer.h.25.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
252
+ "transformer.h.25.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
253
+ "transformer.h.26.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
254
+ "transformer.h.26.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
255
+ "transformer.h.26.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
256
+ "transformer.h.26.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
257
+ "transformer.h.26.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
258
+ "transformer.h.26.ln_1.bias": "model-00002-of-00003.safetensors",
259
+ "transformer.h.26.ln_1.weight": "model-00002-of-00003.safetensors",
260
+ "transformer.h.26.ln_2.bias": "model-00002-of-00003.safetensors",
261
+ "transformer.h.26.ln_2.weight": "model-00002-of-00003.safetensors",
262
+ "transformer.h.26.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
263
+ "transformer.h.26.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
264
+ "transformer.h.26.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
265
+ "transformer.h.26.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
266
+ "transformer.h.27.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
267
+ "transformer.h.27.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
268
+ "transformer.h.27.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
269
+ "transformer.h.27.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
270
+ "transformer.h.27.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
271
+ "transformer.h.27.ln_1.bias": "model-00002-of-00003.safetensors",
272
+ "transformer.h.27.ln_1.weight": "model-00002-of-00003.safetensors",
273
+ "transformer.h.27.ln_2.bias": "model-00002-of-00003.safetensors",
274
+ "transformer.h.27.ln_2.weight": "model-00002-of-00003.safetensors",
275
+ "transformer.h.27.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
276
+ "transformer.h.27.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
277
+ "transformer.h.27.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
278
+ "transformer.h.27.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
279
+ "transformer.h.28.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
280
+ "transformer.h.28.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
281
+ "transformer.h.28.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
282
+ "transformer.h.28.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
283
+ "transformer.h.28.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
284
+ "transformer.h.28.ln_1.bias": "model-00002-of-00003.safetensors",
285
+ "transformer.h.28.ln_1.weight": "model-00002-of-00003.safetensors",
286
+ "transformer.h.28.ln_2.bias": "model-00002-of-00003.safetensors",
287
+ "transformer.h.28.ln_2.weight": "model-00002-of-00003.safetensors",
288
+ "transformer.h.28.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
289
+ "transformer.h.28.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
290
+ "transformer.h.28.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
291
+ "transformer.h.28.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
292
+ "transformer.h.29.attn.attention.k_proj.weight": "model-00002-of-00003.safetensors",
293
+ "transformer.h.29.attn.attention.out_proj.bias": "model-00002-of-00003.safetensors",
294
+ "transformer.h.29.attn.attention.out_proj.weight": "model-00002-of-00003.safetensors",
295
+ "transformer.h.29.attn.attention.q_proj.weight": "model-00002-of-00003.safetensors",
296
+ "transformer.h.29.attn.attention.v_proj.weight": "model-00002-of-00003.safetensors",
297
+ "transformer.h.29.ln_1.bias": "model-00002-of-00003.safetensors",
298
+ "transformer.h.29.ln_1.weight": "model-00002-of-00003.safetensors",
299
+ "transformer.h.29.ln_2.bias": "model-00002-of-00003.safetensors",
300
+ "transformer.h.29.ln_2.weight": "model-00002-of-00003.safetensors",
301
+ "transformer.h.29.mlp.c_fc.bias": "model-00002-of-00003.safetensors",
302
+ "transformer.h.29.mlp.c_fc.weight": "model-00002-of-00003.safetensors",
303
+ "transformer.h.29.mlp.c_proj.bias": "model-00002-of-00003.safetensors",
304
+ "transformer.h.29.mlp.c_proj.weight": "model-00002-of-00003.safetensors",
305
+ "transformer.h.3.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
306
+ "transformer.h.3.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
307
+ "transformer.h.3.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
308
+ "transformer.h.3.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
309
+ "transformer.h.3.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
310
+ "transformer.h.3.ln_1.bias": "model-00001-of-00003.safetensors",
311
+ "transformer.h.3.ln_1.weight": "model-00001-of-00003.safetensors",
312
+ "transformer.h.3.ln_2.bias": "model-00001-of-00003.safetensors",
313
+ "transformer.h.3.ln_2.weight": "model-00001-of-00003.safetensors",
314
+ "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
315
+ "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
316
+ "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
317
+ "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
318
+ "transformer.h.30.attn.attention.k_proj.weight": "model-00003-of-00003.safetensors",
319
+ "transformer.h.30.attn.attention.out_proj.bias": "model-00003-of-00003.safetensors",
320
+ "transformer.h.30.attn.attention.out_proj.weight": "model-00003-of-00003.safetensors",
321
+ "transformer.h.30.attn.attention.q_proj.weight": "model-00003-of-00003.safetensors",
322
+ "transformer.h.30.attn.attention.v_proj.weight": "model-00003-of-00003.safetensors",
323
+ "transformer.h.30.ln_1.bias": "model-00002-of-00003.safetensors",
324
+ "transformer.h.30.ln_1.weight": "model-00002-of-00003.safetensors",
325
+ "transformer.h.30.ln_2.bias": "model-00003-of-00003.safetensors",
326
+ "transformer.h.30.ln_2.weight": "model-00003-of-00003.safetensors",
327
+ "transformer.h.30.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
328
+ "transformer.h.30.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
329
+ "transformer.h.30.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
330
+ "transformer.h.30.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
331
+ "transformer.h.31.attn.attention.k_proj.weight": "model-00003-of-00003.safetensors",
332
+ "transformer.h.31.attn.attention.out_proj.bias": "model-00003-of-00003.safetensors",
333
+ "transformer.h.31.attn.attention.out_proj.weight": "model-00003-of-00003.safetensors",
334
+ "transformer.h.31.attn.attention.q_proj.weight": "model-00003-of-00003.safetensors",
335
+ "transformer.h.31.attn.attention.v_proj.weight": "model-00003-of-00003.safetensors",
336
+ "transformer.h.31.ln_1.bias": "model-00003-of-00003.safetensors",
337
+ "transformer.h.31.ln_1.weight": "model-00003-of-00003.safetensors",
338
+ "transformer.h.31.ln_2.bias": "model-00003-of-00003.safetensors",
339
+ "transformer.h.31.ln_2.weight": "model-00003-of-00003.safetensors",
340
+ "transformer.h.31.mlp.c_fc.bias": "model-00003-of-00003.safetensors",
341
+ "transformer.h.31.mlp.c_fc.weight": "model-00003-of-00003.safetensors",
342
+ "transformer.h.31.mlp.c_proj.bias": "model-00003-of-00003.safetensors",
343
+ "transformer.h.31.mlp.c_proj.weight": "model-00003-of-00003.safetensors",
344
+ "transformer.h.4.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
345
+ "transformer.h.4.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
346
+ "transformer.h.4.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
347
+ "transformer.h.4.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
348
+ "transformer.h.4.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
349
+ "transformer.h.4.ln_1.bias": "model-00001-of-00003.safetensors",
350
+ "transformer.h.4.ln_1.weight": "model-00001-of-00003.safetensors",
351
+ "transformer.h.4.ln_2.bias": "model-00001-of-00003.safetensors",
352
+ "transformer.h.4.ln_2.weight": "model-00001-of-00003.safetensors",
353
+ "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
354
+ "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
355
+ "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
356
+ "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
357
+ "transformer.h.5.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
358
+ "transformer.h.5.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
359
+ "transformer.h.5.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
360
+ "transformer.h.5.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
361
+ "transformer.h.5.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
362
+ "transformer.h.5.ln_1.bias": "model-00001-of-00003.safetensors",
363
+ "transformer.h.5.ln_1.weight": "model-00001-of-00003.safetensors",
364
+ "transformer.h.5.ln_2.bias": "model-00001-of-00003.safetensors",
365
+ "transformer.h.5.ln_2.weight": "model-00001-of-00003.safetensors",
366
+ "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
367
+ "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
368
+ "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
369
+ "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
370
+ "transformer.h.6.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
371
+ "transformer.h.6.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
372
+ "transformer.h.6.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
373
+ "transformer.h.6.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
374
+ "transformer.h.6.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
375
+ "transformer.h.6.ln_1.bias": "model-00001-of-00003.safetensors",
376
+ "transformer.h.6.ln_1.weight": "model-00001-of-00003.safetensors",
377
+ "transformer.h.6.ln_2.bias": "model-00001-of-00003.safetensors",
378
+ "transformer.h.6.ln_2.weight": "model-00001-of-00003.safetensors",
379
+ "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
380
+ "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
381
+ "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
382
+ "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
383
+ "transformer.h.7.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
384
+ "transformer.h.7.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
385
+ "transformer.h.7.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
386
+ "transformer.h.7.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
387
+ "transformer.h.7.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
388
+ "transformer.h.7.ln_1.bias": "model-00001-of-00003.safetensors",
389
+ "transformer.h.7.ln_1.weight": "model-00001-of-00003.safetensors",
390
+ "transformer.h.7.ln_2.bias": "model-00001-of-00003.safetensors",
391
+ "transformer.h.7.ln_2.weight": "model-00001-of-00003.safetensors",
392
+ "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
393
+ "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
394
+ "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
395
+ "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
396
+ "transformer.h.8.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
397
+ "transformer.h.8.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
398
+ "transformer.h.8.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
399
+ "transformer.h.8.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
400
+ "transformer.h.8.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
401
+ "transformer.h.8.ln_1.bias": "model-00001-of-00003.safetensors",
402
+ "transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
403
+ "transformer.h.8.ln_2.bias": "model-00001-of-00003.safetensors",
404
+ "transformer.h.8.ln_2.weight": "model-00001-of-00003.safetensors",
405
+ "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
406
+ "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
407
+ "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
408
+ "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
409
+ "transformer.h.9.attn.attention.k_proj.weight": "model-00001-of-00003.safetensors",
410
+ "transformer.h.9.attn.attention.out_proj.bias": "model-00001-of-00003.safetensors",
411
+ "transformer.h.9.attn.attention.out_proj.weight": "model-00001-of-00003.safetensors",
412
+ "transformer.h.9.attn.attention.q_proj.weight": "model-00001-of-00003.safetensors",
413
+ "transformer.h.9.attn.attention.v_proj.weight": "model-00001-of-00003.safetensors",
414
+ "transformer.h.9.ln_1.bias": "model-00001-of-00003.safetensors",
415
+ "transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
416
+ "transformer.h.9.ln_2.bias": "model-00001-of-00003.safetensors",
417
+ "transformer.h.9.ln_2.weight": "model-00001-of-00003.safetensors",
418
+ "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00003.safetensors",
419
+ "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00003.safetensors",
420
+ "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00003.safetensors",
421
+ "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00003.safetensors",
422
+ "transformer.ln_f.bias": "model-00003-of-00003.safetensors",
423
+ "transformer.ln_f.weight": "model-00003-of-00003.safetensors",
424
+ "transformer.wpe.weight": "model-00001-of-00003.safetensors",
425
+ "transformer.wte.weight": "model-00001-of-00003.safetensors"
426
+ }
427
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "model_max_length": 2048,
19
+ "pad_token": "<|endoftext|>",
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
22
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a330312962b0a11f240598dd20275d49f2b3457046e0c713045d6647d014f1
3
+ size 4984
vocab.json ADDED
The diff for this file is too large to render. See raw diff