IlyaGusev commited on
Commit
90eb865
1 Parent(s): 3ba195d

Initial commit

Browse files
.gitattributes CHANGED
@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model-00003-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
37
+ model-00004-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
38
+ model-00005-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
39
+ model-00001-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
40
+ model-00002-of-00005.safetensors filter=lfs diff=lfs merge=lfs -text
41
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
42
+ orig_adapter/adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text
README.md DELETED
@@ -1,3 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/saiga_nemo_12b_sft_m10_d18",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 1024000,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 10,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.46.2",
26
+ "unsloth_version": "2024.8",
27
+ "use_cache": true,
28
+ "vocab_size": 131072
29
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "max_length": 1024000,
6
+ "pad_token_id": 10,
7
+ "transformers_version": "4.46.2"
8
+ }
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e033d2ef04ca26431d9636466a177e52495e1d84b9cc63ce9f6565f4929ad5a
3
+ size 4865522496
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76c9ac91f6b3022ad37c7f45631febb412f303da09a7a9def7fc8fedf44312df
3
+ size 4907529424
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5479900c234424c3493a88c58ef77f3b02acb8b2452c0b19ca50aeff398a49f9
3
+ size 4907529456
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd47ae31d3d64deee66b514d2cf0f632ce3f05fd99f3c5be05110b5c81775660
3
+ size 4907529456
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5005c88a39e00c4b8a340ccb95b3c4fc9da7fb6852971e1ee3d0c9feb26061f
3
+ size 4907496272
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 24495564800
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00005-of-00005.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00005.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00005.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00005.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
368
+ "model.norm.weight": "model-00005-of-00005.safetensors"
369
+ }
370
+ }
orig_adapter/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "models/saiga_nemo_12b_sft_m10_d18",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "o_proj",
25
+ "k_proj",
26
+ "v_proj",
27
+ "gate_proj",
28
+ "up_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
orig_adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4368129d6037a7f1f58de36a66b296eb0e5bf1b765af6e38195750ea3343881f
3
+ size 1824599104
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ }
12
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
3
+ size 17078292
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff