Hugging Face's logo

internlm
/
SIM_COT-GPT2-CODI

Safetensors
English
chain-of-thought
implicit-reasoning
multimodal
llama3
instruction-tuned
Eval Results
Model card Files
xet
Community
yuhangzang commited on
Commit
f245c8a
·
verified ·
1 Parent(s): 3e9b7c1

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +5 -0
  2. added_tokens.json +3 -0
  3. assets/coconut_teaser.png +3 -0
  4. assets/gpt2.png +3 -0
  5. assets/llama1b.png +3 -0
  6. assets/llama3b_8b.png +3 -0
  7. merges.txt +0 -0
  8. model-00001-of-00001.safetensors +3 -0
  9. model.safetensors.index.json +405 -0
  10. special_tokens_map.json +24 -0
  11. tokenizer_config.json +31 -0
  12. trainer_state.json +3 -0
  13. training_args.bin +3 -0
  14. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ 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
+ assets/coconut_teaser.png filter=lfs diff=lfs merge=lfs -text
37
+ assets/gpt2.png filter=lfs diff=lfs merge=lfs -text
38
+ assets/llama1b.png filter=lfs diff=lfs merge=lfs -text
39
+ assets/llama3b_8b.png filter=lfs diff=lfs merge=lfs -text
40
+ trainer_state.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
assets/coconut_teaser.png ADDED

Git LFS Details

  • SHA256: 64d5b836d63f96619a3aa5a51d59f28bfe2c0a6f2a9d7f3b4d47853e8c411ec4
  • Pointer size: 132 Bytes
  • Size of remote file: 2.62 MB
assets/gpt2.png ADDED

Git LFS Details

  • SHA256: 5d07913ca7fd6b32e9fcc2ea419de9902d69e6b8d42aead17878e31181e96cdd
  • Pointer size: 131 Bytes
  • Size of remote file: 204 kB
assets/llama1b.png ADDED

Git LFS Details

  • SHA256: b9f6a46f66a9f548634eecde5c490cab1f647a52ed4eb367aca62797aa807aca
  • Pointer size: 131 Bytes
  • Size of remote file: 206 kB
assets/llama3b_8b.png ADDED

Git LFS Details

  • SHA256: d0c7914c11ec4156d7b8740d6fc933b202f1d53f063dfd57432c2cb3e7467c48
  • Pointer size: 131 Bytes
  • Size of remote file: 227 kB
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00001.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eaa159155d1db8e8fa3024b959b1e7640cbd5f78b738a3759b2aa61b80b409d
3
+ size 732436560
model.safetensors.index.json ADDED
@@ -0,0 +1,405 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {},
3
+ "weight_map": {
4
+ "codi.base_model.model.transformer.wte.weight": "model-00001-of-00001.safetensors",
5
+ "codi.base_model.model.transformer.wpe.weight": "model-00001-of-00001.safetensors",
6
+ "codi.base_model.model.transformer.h.0.ln_1.weight": "model-00001-of-00001.safetensors",
7
+ "codi.base_model.model.transformer.h.0.ln_1.bias": "model-00001-of-00001.safetensors",
8
+ "codi.base_model.model.transformer.h.0.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
9
+ "codi.base_model.model.transformer.h.0.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
10
+ "codi.base_model.model.transformer.h.0.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
11
+ "codi.base_model.model.transformer.h.0.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
12
+ "codi.base_model.model.transformer.h.0.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
13
+ "codi.base_model.model.transformer.h.0.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
14
+ "codi.base_model.model.transformer.h.0.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
15
+ "codi.base_model.model.transformer.h.0.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
16
+ "codi.base_model.model.transformer.h.0.ln_2.weight": "model-00001-of-00001.safetensors",
17
+ "codi.base_model.model.transformer.h.0.ln_2.bias": "model-00001-of-00001.safetensors",
18
+ "codi.base_model.model.transformer.h.0.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
19
+ "codi.base_model.model.transformer.h.0.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
20
+ "codi.base_model.model.transformer.h.0.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
21
+ "codi.base_model.model.transformer.h.0.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
22
+ "codi.base_model.model.transformer.h.0.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
23
+ "codi.base_model.model.transformer.h.0.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
24
+ "codi.base_model.model.transformer.h.0.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
25
+ "codi.base_model.model.transformer.h.0.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
26
+ "codi.base_model.model.transformer.h.1.ln_1.weight": "model-00001-of-00001.safetensors",
27
+ "codi.base_model.model.transformer.h.1.ln_1.bias": "model-00001-of-00001.safetensors",
28
+ "codi.base_model.model.transformer.h.1.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
29
+ "codi.base_model.model.transformer.h.1.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
30
+ "codi.base_model.model.transformer.h.1.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
31
+ "codi.base_model.model.transformer.h.1.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
32
+ "codi.base_model.model.transformer.h.1.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
33
+ "codi.base_model.model.transformer.h.1.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
34
+ "codi.base_model.model.transformer.h.1.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
35
+ "codi.base_model.model.transformer.h.1.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
36
+ "codi.base_model.model.transformer.h.1.ln_2.weight": "model-00001-of-00001.safetensors",
37
+ "codi.base_model.model.transformer.h.1.ln_2.bias": "model-00001-of-00001.safetensors",
38
+ "codi.base_model.model.transformer.h.1.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
39
+ "codi.base_model.model.transformer.h.1.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
40
+ "codi.base_model.model.transformer.h.1.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
41
+ "codi.base_model.model.transformer.h.1.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
42
+ "codi.base_model.model.transformer.h.1.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
43
+ "codi.base_model.model.transformer.h.1.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
44
+ "codi.base_model.model.transformer.h.1.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
45
+ "codi.base_model.model.transformer.h.1.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
46
+ "codi.base_model.model.transformer.h.2.ln_1.weight": "model-00001-of-00001.safetensors",
47
+ "codi.base_model.model.transformer.h.2.ln_1.bias": "model-00001-of-00001.safetensors",
48
+ "codi.base_model.model.transformer.h.2.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
49
+ "codi.base_model.model.transformer.h.2.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
50
+ "codi.base_model.model.transformer.h.2.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
51
+ "codi.base_model.model.transformer.h.2.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
52
+ "codi.base_model.model.transformer.h.2.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
53
+ "codi.base_model.model.transformer.h.2.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
54
+ "codi.base_model.model.transformer.h.2.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
55
+ "codi.base_model.model.transformer.h.2.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
56
+ "codi.base_model.model.transformer.h.2.ln_2.weight": "model-00001-of-00001.safetensors",
57
+ "codi.base_model.model.transformer.h.2.ln_2.bias": "model-00001-of-00001.safetensors",
58
+ "codi.base_model.model.transformer.h.2.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
59
+ "codi.base_model.model.transformer.h.2.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
60
+ "codi.base_model.model.transformer.h.2.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
61
+ "codi.base_model.model.transformer.h.2.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
62
+ "codi.base_model.model.transformer.h.2.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
63
+ "codi.base_model.model.transformer.h.2.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
64
+ "codi.base_model.model.transformer.h.2.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
65
+ "codi.base_model.model.transformer.h.2.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
66
+ "codi.base_model.model.transformer.h.3.ln_1.weight": "model-00001-of-00001.safetensors",
67
+ "codi.base_model.model.transformer.h.3.ln_1.bias": "model-00001-of-00001.safetensors",
68
+ "codi.base_model.model.transformer.h.3.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
69
+ "codi.base_model.model.transformer.h.3.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
70
+ "codi.base_model.model.transformer.h.3.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
71
+ "codi.base_model.model.transformer.h.3.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
72
+ "codi.base_model.model.transformer.h.3.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
73
+ "codi.base_model.model.transformer.h.3.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
74
+ "codi.base_model.model.transformer.h.3.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
75
+ "codi.base_model.model.transformer.h.3.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
76
+ "codi.base_model.model.transformer.h.3.ln_2.weight": "model-00001-of-00001.safetensors",
77
+ "codi.base_model.model.transformer.h.3.ln_2.bias": "model-00001-of-00001.safetensors",
78
+ "codi.base_model.model.transformer.h.3.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
79
+ "codi.base_model.model.transformer.h.3.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
80
+ "codi.base_model.model.transformer.h.3.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
81
+ "codi.base_model.model.transformer.h.3.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
82
+ "codi.base_model.model.transformer.h.3.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
83
+ "codi.base_model.model.transformer.h.3.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
84
+ "codi.base_model.model.transformer.h.3.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
85
+ "codi.base_model.model.transformer.h.3.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
86
+ "codi.base_model.model.transformer.h.4.ln_1.weight": "model-00001-of-00001.safetensors",
87
+ "codi.base_model.model.transformer.h.4.ln_1.bias": "model-00001-of-00001.safetensors",
88
+ "codi.base_model.model.transformer.h.4.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
89
+ "codi.base_model.model.transformer.h.4.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
90
+ "codi.base_model.model.transformer.h.4.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
91
+ "codi.base_model.model.transformer.h.4.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
92
+ "codi.base_model.model.transformer.h.4.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
93
+ "codi.base_model.model.transformer.h.4.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
94
+ "codi.base_model.model.transformer.h.4.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
95
+ "codi.base_model.model.transformer.h.4.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
96
+ "codi.base_model.model.transformer.h.4.ln_2.weight": "model-00001-of-00001.safetensors",
97
+ "codi.base_model.model.transformer.h.4.ln_2.bias": "model-00001-of-00001.safetensors",
98
+ "codi.base_model.model.transformer.h.4.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
99
+ "codi.base_model.model.transformer.h.4.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
100
+ "codi.base_model.model.transformer.h.4.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
101
+ "codi.base_model.model.transformer.h.4.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
102
+ "codi.base_model.model.transformer.h.4.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
103
+ "codi.base_model.model.transformer.h.4.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
104
+ "codi.base_model.model.transformer.h.4.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
105
+ "codi.base_model.model.transformer.h.4.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
106
+ "codi.base_model.model.transformer.h.5.ln_1.weight": "model-00001-of-00001.safetensors",
107
+ "codi.base_model.model.transformer.h.5.ln_1.bias": "model-00001-of-00001.safetensors",
108
+ "codi.base_model.model.transformer.h.5.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
109
+ "codi.base_model.model.transformer.h.5.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
110
+ "codi.base_model.model.transformer.h.5.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
111
+ "codi.base_model.model.transformer.h.5.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
112
+ "codi.base_model.model.transformer.h.5.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
113
+ "codi.base_model.model.transformer.h.5.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
114
+ "codi.base_model.model.transformer.h.5.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
115
+ "codi.base_model.model.transformer.h.5.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
116
+ "codi.base_model.model.transformer.h.5.ln_2.weight": "model-00001-of-00001.safetensors",
117
+ "codi.base_model.model.transformer.h.5.ln_2.bias": "model-00001-of-00001.safetensors",
118
+ "codi.base_model.model.transformer.h.5.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
119
+ "codi.base_model.model.transformer.h.5.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
120
+ "codi.base_model.model.transformer.h.5.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
121
+ "codi.base_model.model.transformer.h.5.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
122
+ "codi.base_model.model.transformer.h.5.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
123
+ "codi.base_model.model.transformer.h.5.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
124
+ "codi.base_model.model.transformer.h.5.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
125
+ "codi.base_model.model.transformer.h.5.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
126
+ "codi.base_model.model.transformer.h.6.ln_1.weight": "model-00001-of-00001.safetensors",
127
+ "codi.base_model.model.transformer.h.6.ln_1.bias": "model-00001-of-00001.safetensors",
128
+ "codi.base_model.model.transformer.h.6.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
129
+ "codi.base_model.model.transformer.h.6.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
130
+ "codi.base_model.model.transformer.h.6.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
131
+ "codi.base_model.model.transformer.h.6.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
132
+ "codi.base_model.model.transformer.h.6.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
133
+ "codi.base_model.model.transformer.h.6.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
134
+ "codi.base_model.model.transformer.h.6.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
135
+ "codi.base_model.model.transformer.h.6.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
136
+ "codi.base_model.model.transformer.h.6.ln_2.weight": "model-00001-of-00001.safetensors",
137
+ "codi.base_model.model.transformer.h.6.ln_2.bias": "model-00001-of-00001.safetensors",
138
+ "codi.base_model.model.transformer.h.6.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
139
+ "codi.base_model.model.transformer.h.6.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
140
+ "codi.base_model.model.transformer.h.6.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
141
+ "codi.base_model.model.transformer.h.6.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
142
+ "codi.base_model.model.transformer.h.6.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
143
+ "codi.base_model.model.transformer.h.6.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
144
+ "codi.base_model.model.transformer.h.6.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
145
+ "codi.base_model.model.transformer.h.6.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
146
+ "codi.base_model.model.transformer.h.7.ln_1.weight": "model-00001-of-00001.safetensors",
147
+ "codi.base_model.model.transformer.h.7.ln_1.bias": "model-00001-of-00001.safetensors",
148
+ "codi.base_model.model.transformer.h.7.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
149
+ "codi.base_model.model.transformer.h.7.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
150
+ "codi.base_model.model.transformer.h.7.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
151
+ "codi.base_model.model.transformer.h.7.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
152
+ "codi.base_model.model.transformer.h.7.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
153
+ "codi.base_model.model.transformer.h.7.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
154
+ "codi.base_model.model.transformer.h.7.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
155
+ "codi.base_model.model.transformer.h.7.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
156
+ "codi.base_model.model.transformer.h.7.ln_2.weight": "model-00001-of-00001.safetensors",
157
+ "codi.base_model.model.transformer.h.7.ln_2.bias": "model-00001-of-00001.safetensors",
158
+ "codi.base_model.model.transformer.h.7.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
159
+ "codi.base_model.model.transformer.h.7.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
160
+ "codi.base_model.model.transformer.h.7.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
161
+ "codi.base_model.model.transformer.h.7.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
162
+ "codi.base_model.model.transformer.h.7.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
163
+ "codi.base_model.model.transformer.h.7.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
164
+ "codi.base_model.model.transformer.h.7.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
165
+ "codi.base_model.model.transformer.h.7.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
166
+ "codi.base_model.model.transformer.h.8.ln_1.weight": "model-00001-of-00001.safetensors",
167
+ "codi.base_model.model.transformer.h.8.ln_1.bias": "model-00001-of-00001.safetensors",
168
+ "codi.base_model.model.transformer.h.8.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
169
+ "codi.base_model.model.transformer.h.8.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
170
+ "codi.base_model.model.transformer.h.8.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
171
+ "codi.base_model.model.transformer.h.8.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
172
+ "codi.base_model.model.transformer.h.8.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
173
+ "codi.base_model.model.transformer.h.8.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
174
+ "codi.base_model.model.transformer.h.8.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
175
+ "codi.base_model.model.transformer.h.8.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
176
+ "codi.base_model.model.transformer.h.8.ln_2.weight": "model-00001-of-00001.safetensors",
177
+ "codi.base_model.model.transformer.h.8.ln_2.bias": "model-00001-of-00001.safetensors",
178
+ "codi.base_model.model.transformer.h.8.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
179
+ "codi.base_model.model.transformer.h.8.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
180
+ "codi.base_model.model.transformer.h.8.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
181
+ "codi.base_model.model.transformer.h.8.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
182
+ "codi.base_model.model.transformer.h.8.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
183
+ "codi.base_model.model.transformer.h.8.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
184
+ "codi.base_model.model.transformer.h.8.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
185
+ "codi.base_model.model.transformer.h.8.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
186
+ "codi.base_model.model.transformer.h.9.ln_1.weight": "model-00001-of-00001.safetensors",
187
+ "codi.base_model.model.transformer.h.9.ln_1.bias": "model-00001-of-00001.safetensors",
188
+ "codi.base_model.model.transformer.h.9.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
189
+ "codi.base_model.model.transformer.h.9.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
190
+ "codi.base_model.model.transformer.h.9.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
191
+ "codi.base_model.model.transformer.h.9.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
192
+ "codi.base_model.model.transformer.h.9.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
193
+ "codi.base_model.model.transformer.h.9.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
194
+ "codi.base_model.model.transformer.h.9.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
195
+ "codi.base_model.model.transformer.h.9.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
196
+ "codi.base_model.model.transformer.h.9.ln_2.weight": "model-00001-of-00001.safetensors",
197
+ "codi.base_model.model.transformer.h.9.ln_2.bias": "model-00001-of-00001.safetensors",
198
+ "codi.base_model.model.transformer.h.9.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
199
+ "codi.base_model.model.transformer.h.9.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
200
+ "codi.base_model.model.transformer.h.9.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
201
+ "codi.base_model.model.transformer.h.9.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
202
+ "codi.base_model.model.transformer.h.9.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
203
+ "codi.base_model.model.transformer.h.9.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
204
+ "codi.base_model.model.transformer.h.9.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
205
+ "codi.base_model.model.transformer.h.9.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
206
+ "codi.base_model.model.transformer.h.10.ln_1.weight": "model-00001-of-00001.safetensors",
207
+ "codi.base_model.model.transformer.h.10.ln_1.bias": "model-00001-of-00001.safetensors",
208
+ "codi.base_model.model.transformer.h.10.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
209
+ "codi.base_model.model.transformer.h.10.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
210
+ "codi.base_model.model.transformer.h.10.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
211
+ "codi.base_model.model.transformer.h.10.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
212
+ "codi.base_model.model.transformer.h.10.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
213
+ "codi.base_model.model.transformer.h.10.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
214
+ "codi.base_model.model.transformer.h.10.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
215
+ "codi.base_model.model.transformer.h.10.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
216
+ "codi.base_model.model.transformer.h.10.ln_2.weight": "model-00001-of-00001.safetensors",
217
+ "codi.base_model.model.transformer.h.10.ln_2.bias": "model-00001-of-00001.safetensors",
218
+ "codi.base_model.model.transformer.h.10.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
219
+ "codi.base_model.model.transformer.h.10.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
220
+ "codi.base_model.model.transformer.h.10.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
221
+ "codi.base_model.model.transformer.h.10.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
222
+ "codi.base_model.model.transformer.h.10.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
223
+ "codi.base_model.model.transformer.h.10.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
224
+ "codi.base_model.model.transformer.h.10.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
225
+ "codi.base_model.model.transformer.h.10.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
226
+ "codi.base_model.model.transformer.h.11.ln_1.weight": "model-00001-of-00001.safetensors",
227
+ "codi.base_model.model.transformer.h.11.ln_1.bias": "model-00001-of-00001.safetensors",
228
+ "codi.base_model.model.transformer.h.11.attn.c_attn.base_layer.weight": "model-00001-of-00001.safetensors",
229
+ "codi.base_model.model.transformer.h.11.attn.c_attn.base_layer.bias": "model-00001-of-00001.safetensors",
230
+ "codi.base_model.model.transformer.h.11.attn.c_attn.lora_A.default.weight": "model-00001-of-00001.safetensors",
231
+ "codi.base_model.model.transformer.h.11.attn.c_attn.lora_B.default.weight": "model-00001-of-00001.safetensors",
232
+ "codi.base_model.model.transformer.h.11.attn.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
233
+ "codi.base_model.model.transformer.h.11.attn.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
234
+ "codi.base_model.model.transformer.h.11.attn.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
235
+ "codi.base_model.model.transformer.h.11.attn.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
236
+ "codi.base_model.model.transformer.h.11.ln_2.weight": "model-00001-of-00001.safetensors",
237
+ "codi.base_model.model.transformer.h.11.ln_2.bias": "model-00001-of-00001.safetensors",
238
+ "codi.base_model.model.transformer.h.11.mlp.c_fc.base_layer.weight": "model-00001-of-00001.safetensors",
239
+ "codi.base_model.model.transformer.h.11.mlp.c_fc.base_layer.bias": "model-00001-of-00001.safetensors",
240
+ "codi.base_model.model.transformer.h.11.mlp.c_fc.lora_A.default.weight": "model-00001-of-00001.safetensors",
241
+ "codi.base_model.model.transformer.h.11.mlp.c_fc.lora_B.default.weight": "model-00001-of-00001.safetensors",
242
+ "codi.base_model.model.transformer.h.11.mlp.c_proj.base_layer.weight": "model-00001-of-00001.safetensors",
243
+ "codi.base_model.model.transformer.h.11.mlp.c_proj.base_layer.bias": "model-00001-of-00001.safetensors",
244
+ "codi.base_model.model.transformer.h.11.mlp.c_proj.lora_A.default.weight": "model-00001-of-00001.safetensors",
245
+ "codi.base_model.model.transformer.h.11.mlp.c_proj.lora_B.default.weight": "model-00001-of-00001.safetensors",
246
+ "codi.base_model.model.transformer.ln_f.weight": "model-00001-of-00001.safetensors",
247
+ "codi.base_model.model.transformer.ln_f.bias": "model-00001-of-00001.safetensors",
248
+ "codi.base_model.model.lm_head.weight": "model-00001-of-00001.safetensors",
249
+ "decoder.transformer.wte.weight": "model-00001-of-00001.safetensors",
250
+ "decoder.transformer.wpe.weight": "model-00001-of-00001.safetensors",
251
+ "decoder.transformer.h.0.ln_1.weight": "model-00001-of-00001.safetensors",
252
+ "decoder.transformer.h.0.ln_1.bias": "model-00001-of-00001.safetensors",
253
+ "decoder.transformer.h.0.attn.c_attn.weight": "model-00001-of-00001.safetensors",
254
+ "decoder.transformer.h.0.attn.c_attn.bias": "model-00001-of-00001.safetensors",
255
+ "decoder.transformer.h.0.attn.c_proj.weight": "model-00001-of-00001.safetensors",
256
+ "decoder.transformer.h.0.attn.c_proj.bias": "model-00001-of-00001.safetensors",
257
+ "decoder.transformer.h.0.ln_2.weight": "model-00001-of-00001.safetensors",
258
+ "decoder.transformer.h.0.ln_2.bias": "model-00001-of-00001.safetensors",
259
+ "decoder.transformer.h.0.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
260
+ "decoder.transformer.h.0.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
261
+ "decoder.transformer.h.0.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
262
+ "decoder.transformer.h.0.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
263
+ "decoder.transformer.h.1.ln_1.weight": "model-00001-of-00001.safetensors",
264
+ "decoder.transformer.h.1.ln_1.bias": "model-00001-of-00001.safetensors",
265
+ "decoder.transformer.h.1.attn.c_attn.weight": "model-00001-of-00001.safetensors",
266
+ "decoder.transformer.h.1.attn.c_attn.bias": "model-00001-of-00001.safetensors",
267
+ "decoder.transformer.h.1.attn.c_proj.weight": "model-00001-of-00001.safetensors",
268
+ "decoder.transformer.h.1.attn.c_proj.bias": "model-00001-of-00001.safetensors",
269
+ "decoder.transformer.h.1.ln_2.weight": "model-00001-of-00001.safetensors",
270
+ "decoder.transformer.h.1.ln_2.bias": "model-00001-of-00001.safetensors",
271
+ "decoder.transformer.h.1.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
272
+ "decoder.transformer.h.1.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
273
+ "decoder.transformer.h.1.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
274
+ "decoder.transformer.h.1.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
275
+ "decoder.transformer.h.2.ln_1.weight": "model-00001-of-00001.safetensors",
276
+ "decoder.transformer.h.2.ln_1.bias": "model-00001-of-00001.safetensors",
277
+ "decoder.transformer.h.2.attn.c_attn.weight": "model-00001-of-00001.safetensors",
278
+ "decoder.transformer.h.2.attn.c_attn.bias": "model-00001-of-00001.safetensors",
279
+ "decoder.transformer.h.2.attn.c_proj.weight": "model-00001-of-00001.safetensors",
280
+ "decoder.transformer.h.2.attn.c_proj.bias": "model-00001-of-00001.safetensors",
281
+ "decoder.transformer.h.2.ln_2.weight": "model-00001-of-00001.safetensors",
282
+ "decoder.transformer.h.2.ln_2.bias": "model-00001-of-00001.safetensors",
283
+ "decoder.transformer.h.2.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
284
+ "decoder.transformer.h.2.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
285
+ "decoder.transformer.h.2.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
286
+ "decoder.transformer.h.2.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
287
+ "decoder.transformer.h.3.ln_1.weight": "model-00001-of-00001.safetensors",
288
+ "decoder.transformer.h.3.ln_1.bias": "model-00001-of-00001.safetensors",
289
+ "decoder.transformer.h.3.attn.c_attn.weight": "model-00001-of-00001.safetensors",
290
+ "decoder.transformer.h.3.attn.c_attn.bias": "model-00001-of-00001.safetensors",
291
+ "decoder.transformer.h.3.attn.c_proj.weight": "model-00001-of-00001.safetensors",
292
+ "decoder.transformer.h.3.attn.c_proj.bias": "model-00001-of-00001.safetensors",
293
+ "decoder.transformer.h.3.ln_2.weight": "model-00001-of-00001.safetensors",
294
+ "decoder.transformer.h.3.ln_2.bias": "model-00001-of-00001.safetensors",
295
+ "decoder.transformer.h.3.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
296
+ "decoder.transformer.h.3.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
297
+ "decoder.transformer.h.3.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
298
+ "decoder.transformer.h.3.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
299
+ "decoder.transformer.h.4.ln_1.weight": "model-00001-of-00001.safetensors",
300
+ "decoder.transformer.h.4.ln_1.bias": "model-00001-of-00001.safetensors",
301
+ "decoder.transformer.h.4.attn.c_attn.weight": "model-00001-of-00001.safetensors",
302
+ "decoder.transformer.h.4.attn.c_attn.bias": "model-00001-of-00001.safetensors",
303
+ "decoder.transformer.h.4.attn.c_proj.weight": "model-00001-of-00001.safetensors",
304
+ "decoder.transformer.h.4.attn.c_proj.bias": "model-00001-of-00001.safetensors",
305
+ "decoder.transformer.h.4.ln_2.weight": "model-00001-of-00001.safetensors",
306
+ "decoder.transformer.h.4.ln_2.bias": "model-00001-of-00001.safetensors",
307
+ "decoder.transformer.h.4.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
308
+ "decoder.transformer.h.4.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
309
+ "decoder.transformer.h.4.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
310
+ "decoder.transformer.h.4.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
311
+ "decoder.transformer.h.5.ln_1.weight": "model-00001-of-00001.safetensors",
312
+ "decoder.transformer.h.5.ln_1.bias": "model-00001-of-00001.safetensors",
313
+ "decoder.transformer.h.5.attn.c_attn.weight": "model-00001-of-00001.safetensors",
314
+ "decoder.transformer.h.5.attn.c_attn.bias": "model-00001-of-00001.safetensors",
315
+ "decoder.transformer.h.5.attn.c_proj.weight": "model-00001-of-00001.safetensors",
316
+ "decoder.transformer.h.5.attn.c_proj.bias": "model-00001-of-00001.safetensors",
317
+ "decoder.transformer.h.5.ln_2.weight": "model-00001-of-00001.safetensors",
318
+ "decoder.transformer.h.5.ln_2.bias": "model-00001-of-00001.safetensors",
319
+ "decoder.transformer.h.5.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
320
+ "decoder.transformer.h.5.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
321
+ "decoder.transformer.h.5.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
322
+ "decoder.transformer.h.5.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
323
+ "decoder.transformer.h.6.ln_1.weight": "model-00001-of-00001.safetensors",
324
+ "decoder.transformer.h.6.ln_1.bias": "model-00001-of-00001.safetensors",
325
+ "decoder.transformer.h.6.attn.c_attn.weight": "model-00001-of-00001.safetensors",
326
+ "decoder.transformer.h.6.attn.c_attn.bias": "model-00001-of-00001.safetensors",
327
+ "decoder.transformer.h.6.attn.c_proj.weight": "model-00001-of-00001.safetensors",
328
+ "decoder.transformer.h.6.attn.c_proj.bias": "model-00001-of-00001.safetensors",
329
+ "decoder.transformer.h.6.ln_2.weight": "model-00001-of-00001.safetensors",
330
+ "decoder.transformer.h.6.ln_2.bias": "model-00001-of-00001.safetensors",
331
+ "decoder.transformer.h.6.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
332
+ "decoder.transformer.h.6.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
333
+ "decoder.transformer.h.6.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
334
+ "decoder.transformer.h.6.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
335
+ "decoder.transformer.h.7.ln_1.weight": "model-00001-of-00001.safetensors",
336
+ "decoder.transformer.h.7.ln_1.bias": "model-00001-of-00001.safetensors",
337
+ "decoder.transformer.h.7.attn.c_attn.weight": "model-00001-of-00001.safetensors",
338
+ "decoder.transformer.h.7.attn.c_attn.bias": "model-00001-of-00001.safetensors",
339
+ "decoder.transformer.h.7.attn.c_proj.weight": "model-00001-of-00001.safetensors",
340
+ "decoder.transformer.h.7.attn.c_proj.bias": "model-00001-of-00001.safetensors",
341
+ "decoder.transformer.h.7.ln_2.weight": "model-00001-of-00001.safetensors",
342
+ "decoder.transformer.h.7.ln_2.bias": "model-00001-of-00001.safetensors",
343
+ "decoder.transformer.h.7.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
344
+ "decoder.transformer.h.7.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
345
+ "decoder.transformer.h.7.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
346
+ "decoder.transformer.h.7.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
347
+ "decoder.transformer.h.8.ln_1.weight": "model-00001-of-00001.safetensors",
348
+ "decoder.transformer.h.8.ln_1.bias": "model-00001-of-00001.safetensors",
349
+ "decoder.transformer.h.8.attn.c_attn.weight": "model-00001-of-00001.safetensors",
350
+ "decoder.transformer.h.8.attn.c_attn.bias": "model-00001-of-00001.safetensors",
351
+ "decoder.transformer.h.8.attn.c_proj.weight": "model-00001-of-00001.safetensors",
352
+ "decoder.transformer.h.8.attn.c_proj.bias": "model-00001-of-00001.safetensors",
353
+ "decoder.transformer.h.8.ln_2.weight": "model-00001-of-00001.safetensors",
354
+ "decoder.transformer.h.8.ln_2.bias": "model-00001-of-00001.safetensors",
355
+ "decoder.transformer.h.8.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
356
+ "decoder.transformer.h.8.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
357
+ "decoder.transformer.h.8.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
358
+ "decoder.transformer.h.8.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
359
+ "decoder.transformer.h.9.ln_1.weight": "model-00001-of-00001.safetensors",
360
+ "decoder.transformer.h.9.ln_1.bias": "model-00001-of-00001.safetensors",
361
+ "decoder.transformer.h.9.attn.c_attn.weight": "model-00001-of-00001.safetensors",
362
+ "decoder.transformer.h.9.attn.c_attn.bias": "model-00001-of-00001.safetensors",
363
+ "decoder.transformer.h.9.attn.c_proj.weight": "model-00001-of-00001.safetensors",
364
+ "decoder.transformer.h.9.attn.c_proj.bias": "model-00001-of-00001.safetensors",
365
+ "decoder.transformer.h.9.ln_2.weight": "model-00001-of-00001.safetensors",
366
+ "decoder.transformer.h.9.ln_2.bias": "model-00001-of-00001.safetensors",
367
+ "decoder.transformer.h.9.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
368
+ "decoder.transformer.h.9.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
369
+ "decoder.transformer.h.9.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
370
+ "decoder.transformer.h.9.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
371
+ "decoder.transformer.h.10.ln_1.weight": "model-00001-of-00001.safetensors",
372
+ "decoder.transformer.h.10.ln_1.bias": "model-00001-of-00001.safetensors",
373
+ "decoder.transformer.h.10.attn.c_attn.weight": "model-00001-of-00001.safetensors",
374
+ "decoder.transformer.h.10.attn.c_attn.bias": "model-00001-of-00001.safetensors",
375
+ "decoder.transformer.h.10.attn.c_proj.weight": "model-00001-of-00001.safetensors",
376
+ "decoder.transformer.h.10.attn.c_proj.bias": "model-00001-of-00001.safetensors",
377
+ "decoder.transformer.h.10.ln_2.weight": "model-00001-of-00001.safetensors",
378
+ "decoder.transformer.h.10.ln_2.bias": "model-00001-of-00001.safetensors",
379
+ "decoder.transformer.h.10.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
380
+ "decoder.transformer.h.10.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
381
+ "decoder.transformer.h.10.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
382
+ "decoder.transformer.h.10.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
383
+ "decoder.transformer.h.11.ln_1.weight": "model-00001-of-00001.safetensors",
384
+ "decoder.transformer.h.11.ln_1.bias": "model-00001-of-00001.safetensors",
385
+ "decoder.transformer.h.11.attn.c_attn.weight": "model-00001-of-00001.safetensors",
386
+ "decoder.transformer.h.11.attn.c_attn.bias": "model-00001-of-00001.safetensors",
387
+ "decoder.transformer.h.11.attn.c_proj.weight": "model-00001-of-00001.safetensors",
388
+ "decoder.transformer.h.11.attn.c_proj.bias": "model-00001-of-00001.safetensors",
389
+ "decoder.transformer.h.11.ln_2.weight": "model-00001-of-00001.safetensors",
390
+ "decoder.transformer.h.11.ln_2.bias": "model-00001-of-00001.safetensors",
391
+ "decoder.transformer.h.11.mlp.c_fc.weight": "model-00001-of-00001.safetensors",
392
+ "decoder.transformer.h.11.mlp.c_fc.bias": "model-00001-of-00001.safetensors",
393
+ "decoder.transformer.h.11.mlp.c_proj.weight": "model-00001-of-00001.safetensors",
394
+ "decoder.transformer.h.11.mlp.c_proj.bias": "model-00001-of-00001.safetensors",
395
+ "decoder.transformer.ln_f.weight": "model-00001-of-00001.safetensors",
396
+ "decoder.transformer.ln_f.bias": "model-00001-of-00001.safetensors",
397
+ "decoder.lm_head.weight": "model-00001-of-00001.safetensors",
398
+ "prj.1.weight": "model-00001-of-00001.safetensors",
399
+ "prj.1.bias": "model-00001-of-00001.safetensors",
400
+ "prj.3.weight": "model-00001-of-00001.safetensors",
401
+ "prj.3.bias": "model-00001-of-00001.safetensors",
402
+ "prj.ln.weight": "model-00001-of-00001.safetensors",
403
+ "prj.ln.bias": "model-00001-of-00001.safetensors"
404
+ }
405
+ }
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": "[PAD]",
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 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50257": {
14
+ "content": "[PAD]",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ }
21
+ },
22
+ "bos_token": "<|endoftext|>",
23
+ "clean_up_tokenization_spaces": false,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "model_max_length": 512,
27
+ "pad_token": "[PAD]",
28
+ "padding_side": "right",
29
+ "tokenizer_class": "GPT2Tokenizer",
30
+ "unk_token": "<|endoftext|>"
31
+ }
trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeeddbb01720136a9233073c042d665e248f11cfcd83a30502a08672a6b1a89b
3
+ size 13918553
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36036f77a8bbb03877633e3f9a94cbfc4d70d224ab0df8a8d89af0add8d2959e
3
+ size 6200
vocab.json ADDED
The diff for this file is too large to render. See raw diff