Hugging Face's logo

qazimbhat1
/
my-model-repo3

Text Generation
Transformers
PyTorch
English
llava_crystal
nlp
llm
custom_code
Inference Endpoints
Model card Files Community
Qazim Bhat commited on
Commit
551b2c3
•
1 Parent(s): 00ec8b6

Add initial model files

Browse files
Files changed (11) hide show
  1. config.json +52 -0
  2. generation_config.json +6 -0
  3. pytorch_model-00001-of-00002.bin +3 -0
  4. pytorch_model-00002-of-00002.bin +3 -0
  5. pytorch_model.bin.index.json +854 -0
  6. special_tokens_map.json +33 -0
  7. tokenization_crystalcoder_fast.py +144 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +269 -0
  10. trainer_state.json +0 -0
  11. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "LLM360/CrystalChat",
3
+ "activation_function": "swiglu",
4
+ "architectures": [
5
+ "LlavaCrystalForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "LLM360/CrystalChat--configuration_crystalcoder.CrystalCoderConfig",
10
+ "AutoModel": "LLM360/CrystalChat--modeling_crystalcoder.CrystalCoderModel",
11
+ "AutoModelForCausalLM": "LLM360/CrystalChat--modeling_crystalcoder.CrystalCoderLMHeadModel"
12
+ },
13
+ "bos_token_id": 1,
14
+ "embd_pdrop": 0.0,
15
+ "eos_token_id": 2,
16
+ "freeze_mm_mlp_adapter": false,
17
+ "image_aspect_ratio": "pad",
18
+ "initializer_range": 0.02,
19
+ "layer_norm_epsilon": 1e-05,
20
+ "mm_hidden_size": 1024,
21
+ "mm_projector_lr": null,
22
+ "mm_projector_type": "mlp2x_gelu",
23
+ "mm_use_im_patch_token": false,
24
+ "mm_use_im_start_end": false,
25
+ "mm_vision_select_feature": "patch",
26
+ "mm_vision_select_layer": -2,
27
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
28
+ "model_type": "llava_crystal",
29
+ "mup_embeddings_scale": 14.6,
30
+ "mup_output_alpha": 2.22,
31
+ "mup_scale_qk_dot_by_d": true,
32
+ "mup_width_scale": 0.0625,
33
+ "n_embd": 4096,
34
+ "n_head": 32,
35
+ "n_inner": 10922,
36
+ "n_layer": 32,
37
+ "n_positions": 2048,
38
+ "position_embedding_type": "rotary",
39
+ "reorder_and_upcast_attn": false,
40
+ "resid_pdrop": 0.0,
41
+ "rotary_dim": 32,
42
+ "scale_attn_by_inverse_layer_idx": false,
43
+ "scale_attn_weights": true,
44
+ "tokenizer_model_max_length": 2048,
45
+ "tokenizer_padding_side": "right",
46
+ "torch_dtype": "bfloat16",
47
+ "transformers_version": "4.31.0",
48
+ "tune_mm_mlp_adapter": false,
49
+ "use_cache": true,
50
+ "use_mm_proj": true,
51
+ "vocab_size": 32032
52
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.31.0"
6
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d6b4edfb9aec8082fcd8d9258fed4faadb9971fbe05d24115decf6319d6151
3
+ size 9928636172
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4367dc5a6c92e7d99ed155a798628ba231ff52793a651cbf721bc7397ac1a5b1
3
+ size 3871196172
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,854 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13799531776
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00001-of-00002.bin",
7
+ "transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
8
+ "transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
9
+ "transformer.h.0.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
10
+ "transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
11
+ "transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00002.bin",
12
+ "transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00002.bin",
13
+ "transformer.h.0.ln_2.bias": "pytorch_model-00001-of-00002.bin",
14
+ "transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00002.bin",
15
+ "transformer.h.0.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
16
+ "transformer.h.0.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
17
+ "transformer.h.0.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
18
+ "transformer.h.0.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
19
+ "transformer.h.0.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
20
+ "transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
21
+ "transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
22
+ "transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
23
+ "transformer.h.1.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
24
+ "transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
25
+ "transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00002.bin",
26
+ "transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00002.bin",
27
+ "transformer.h.1.ln_2.bias": "pytorch_model-00001-of-00002.bin",
28
+ "transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00002.bin",
29
+ "transformer.h.1.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
30
+ "transformer.h.1.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
31
+ "transformer.h.1.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
32
+ "transformer.h.1.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
33
+ "transformer.h.1.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
34
+ "transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
36
+ "transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
37
+ "transformer.h.10.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
38
+ "transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
39
+ "transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00002.bin",
40
+ "transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00002.bin",
41
+ "transformer.h.10.ln_2.bias": "pytorch_model-00001-of-00002.bin",
42
+ "transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00002.bin",
43
+ "transformer.h.10.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
44
+ "transformer.h.10.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
45
+ "transformer.h.10.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
46
+ "transformer.h.10.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
47
+ "transformer.h.10.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
48
+ "transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
49
+ "transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
50
+ "transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
51
+ "transformer.h.11.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
52
+ "transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
53
+ "transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00002.bin",
54
+ "transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00002.bin",
55
+ "transformer.h.11.ln_2.bias": "pytorch_model-00001-of-00002.bin",
56
+ "transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00002.bin",
57
+ "transformer.h.11.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
58
+ "transformer.h.11.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
59
+ "transformer.h.11.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
60
+ "transformer.h.11.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
61
+ "transformer.h.11.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
62
+ "transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
63
+ "transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
64
+ "transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
65
+ "transformer.h.12.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
66
+ "transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "transformer.h.12.ln_1.bias": "pytorch_model-00001-of-00002.bin",
68
+ "transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00002.bin",
69
+ "transformer.h.12.ln_2.bias": "pytorch_model-00001-of-00002.bin",
70
+ "transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00002.bin",
71
+ "transformer.h.12.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
72
+ "transformer.h.12.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
73
+ "transformer.h.12.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
74
+ "transformer.h.12.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
75
+ "transformer.h.12.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
76
+ "transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
77
+ "transformer.h.13.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
78
+ "transformer.h.13.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
79
+ "transformer.h.13.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
80
+ "transformer.h.13.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
81
+ "transformer.h.13.ln_1.bias": "pytorch_model-00001-of-00002.bin",
82
+ "transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00002.bin",
83
+ "transformer.h.13.ln_2.bias": "pytorch_model-00001-of-00002.bin",
84
+ "transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00002.bin",
85
+ "transformer.h.13.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
86
+ "transformer.h.13.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
87
+ "transformer.h.13.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
88
+ "transformer.h.13.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
89
+ "transformer.h.13.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
90
+ "transformer.h.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
91
+ "transformer.h.14.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
92
+ "transformer.h.14.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
93
+ "transformer.h.14.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
94
+ "transformer.h.14.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
95
+ "transformer.h.14.ln_1.bias": "pytorch_model-00001-of-00002.bin",
96
+ "transformer.h.14.ln_1.weight": "pytorch_model-00001-of-00002.bin",
97
+ "transformer.h.14.ln_2.bias": "pytorch_model-00001-of-00002.bin",
98
+ "transformer.h.14.ln_2.weight": "pytorch_model-00001-of-00002.bin",
99
+ "transformer.h.14.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
100
+ "transformer.h.14.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
101
+ "transformer.h.14.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
102
+ "transformer.h.14.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
103
+ "transformer.h.14.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
104
+ "transformer.h.14.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
105
+ "transformer.h.15.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
106
+ "transformer.h.15.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
107
+ "transformer.h.15.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
108
+ "transformer.h.15.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
109
+ "transformer.h.15.ln_1.bias": "pytorch_model-00001-of-00002.bin",
110
+ "transformer.h.15.ln_1.weight": "pytorch_model-00001-of-00002.bin",
111
+ "transformer.h.15.ln_2.bias": "pytorch_model-00001-of-00002.bin",
112
+ "transformer.h.15.ln_2.weight": "pytorch_model-00001-of-00002.bin",
113
+ "transformer.h.15.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
114
+ "transformer.h.15.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
115
+ "transformer.h.15.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
116
+ "transformer.h.15.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
117
+ "transformer.h.15.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
118
+ "transformer.h.15.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
119
+ "transformer.h.16.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
120
+ "transformer.h.16.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
121
+ "transformer.h.16.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
122
+ "transformer.h.16.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
123
+ "transformer.h.16.ln_1.bias": "pytorch_model-00001-of-00002.bin",
124
+ "transformer.h.16.ln_1.weight": "pytorch_model-00001-of-00002.bin",
125
+ "transformer.h.16.ln_2.bias": "pytorch_model-00001-of-00002.bin",
126
+ "transformer.h.16.ln_2.weight": "pytorch_model-00001-of-00002.bin",
127
+ "transformer.h.16.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
128
+ "transformer.h.16.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
129
+ "transformer.h.16.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
130
+ "transformer.h.16.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
131
+ "transformer.h.16.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
132
+ "transformer.h.16.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
133
+ "transformer.h.17.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
134
+ "transformer.h.17.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
135
+ "transformer.h.17.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
136
+ "transformer.h.17.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
137
+ "transformer.h.17.ln_1.bias": "pytorch_model-00001-of-00002.bin",
138
+ "transformer.h.17.ln_1.weight": "pytorch_model-00001-of-00002.bin",
139
+ "transformer.h.17.ln_2.bias": "pytorch_model-00001-of-00002.bin",
140
+ "transformer.h.17.ln_2.weight": "pytorch_model-00001-of-00002.bin",
141
+ "transformer.h.17.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
142
+ "transformer.h.17.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
143
+ "transformer.h.17.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
144
+ "transformer.h.17.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
145
+ "transformer.h.17.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
146
+ "transformer.h.17.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
147
+ "transformer.h.18.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
148
+ "transformer.h.18.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
149
+ "transformer.h.18.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
150
+ "transformer.h.18.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
151
+ "transformer.h.18.ln_1.bias": "pytorch_model-00001-of-00002.bin",
152
+ "transformer.h.18.ln_1.weight": "pytorch_model-00001-of-00002.bin",
153
+ "transformer.h.18.ln_2.bias": "pytorch_model-00001-of-00002.bin",
154
+ "transformer.h.18.ln_2.weight": "pytorch_model-00001-of-00002.bin",
155
+ "transformer.h.18.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
156
+ "transformer.h.18.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
157
+ "transformer.h.18.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
158
+ "transformer.h.18.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
159
+ "transformer.h.18.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
160
+ "transformer.h.18.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
161
+ "transformer.h.19.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
162
+ "transformer.h.19.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
163
+ "transformer.h.19.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
164
+ "transformer.h.19.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
165
+ "transformer.h.19.ln_1.bias": "pytorch_model-00001-of-00002.bin",
166
+ "transformer.h.19.ln_1.weight": "pytorch_model-00001-of-00002.bin",
167
+ "transformer.h.19.ln_2.bias": "pytorch_model-00001-of-00002.bin",
168
+ "transformer.h.19.ln_2.weight": "pytorch_model-00001-of-00002.bin",
169
+ "transformer.h.19.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
170
+ "transformer.h.19.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
171
+ "transformer.h.19.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
172
+ "transformer.h.19.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
173
+ "transformer.h.19.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
174
+ "transformer.h.19.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
175
+ "transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
176
+ "transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
177
+ "transformer.h.2.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
178
+ "transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
179
+ "transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00002.bin",
180
+ "transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00002.bin",
181
+ "transformer.h.2.ln_2.bias": "pytorch_model-00001-of-00002.bin",
182
+ "transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00002.bin",
183
+ "transformer.h.2.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
184
+ "transformer.h.2.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
185
+ "transformer.h.2.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
186
+ "transformer.h.2.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
187
+ "transformer.h.2.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
188
+ "transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
189
+ "transformer.h.20.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
190
+ "transformer.h.20.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
191
+ "transformer.h.20.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
192
+ "transformer.h.20.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
193
+ "transformer.h.20.ln_1.bias": "pytorch_model-00001-of-00002.bin",
194
+ "transformer.h.20.ln_1.weight": "pytorch_model-00001-of-00002.bin",
195
+ "transformer.h.20.ln_2.bias": "pytorch_model-00001-of-00002.bin",
196
+ "transformer.h.20.ln_2.weight": "pytorch_model-00001-of-00002.bin",
197
+ "transformer.h.20.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
198
+ "transformer.h.20.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
199
+ "transformer.h.20.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
200
+ "transformer.h.20.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
201
+ "transformer.h.20.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
202
+ "transformer.h.20.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
203
+ "transformer.h.21.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
204
+ "transformer.h.21.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
205
+ "transformer.h.21.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
206
+ "transformer.h.21.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
207
+ "transformer.h.21.ln_1.bias": "pytorch_model-00001-of-00002.bin",
208
+ "transformer.h.21.ln_1.weight": "pytorch_model-00001-of-00002.bin",
209
+ "transformer.h.21.ln_2.bias": "pytorch_model-00001-of-00002.bin",
210
+ "transformer.h.21.ln_2.weight": "pytorch_model-00001-of-00002.bin",
211
+ "transformer.h.21.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
212
+ "transformer.h.21.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
213
+ "transformer.h.21.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
214
+ "transformer.h.21.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
215
+ "transformer.h.21.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
216
+ "transformer.h.21.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
217
+ "transformer.h.22.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
218
+ "transformer.h.22.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
219
+ "transformer.h.22.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
220
+ "transformer.h.22.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
221
+ "transformer.h.22.ln_1.bias": "pytorch_model-00001-of-00002.bin",
222
+ "transformer.h.22.ln_1.weight": "pytorch_model-00001-of-00002.bin",
223
+ "transformer.h.22.ln_2.bias": "pytorch_model-00001-of-00002.bin",
224
+ "transformer.h.22.ln_2.weight": "pytorch_model-00001-of-00002.bin",
225
+ "transformer.h.22.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
226
+ "transformer.h.22.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
227
+ "transformer.h.22.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
228
+ "transformer.h.22.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
229
+ "transformer.h.22.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
230
+ "transformer.h.22.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
231
+ "transformer.h.23.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
232
+ "transformer.h.23.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
233
+ "transformer.h.23.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
234
+ "transformer.h.23.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
235
+ "transformer.h.23.ln_1.bias": "pytorch_model-00001-of-00002.bin",
236
+ "transformer.h.23.ln_1.weight": "pytorch_model-00001-of-00002.bin",
237
+ "transformer.h.23.ln_2.bias": "pytorch_model-00001-of-00002.bin",
238
+ "transformer.h.23.ln_2.weight": "pytorch_model-00001-of-00002.bin",
239
+ "transformer.h.23.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
240
+ "transformer.h.23.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
241
+ "transformer.h.23.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
242
+ "transformer.h.23.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
243
+ "transformer.h.23.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
244
+ "transformer.h.23.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
245
+ "transformer.h.24.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
246
+ "transformer.h.24.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
247
+ "transformer.h.24.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
248
+ "transformer.h.24.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
249
+ "transformer.h.24.ln_1.bias": "pytorch_model-00001-of-00002.bin",
250
+ "transformer.h.24.ln_1.weight": "pytorch_model-00001-of-00002.bin",
251
+ "transformer.h.24.ln_2.bias": "pytorch_model-00002-of-00002.bin",
252
+ "transformer.h.24.ln_2.weight": "pytorch_model-00002-of-00002.bin",
253
+ "transformer.h.24.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
254
+ "transformer.h.24.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
255
+ "transformer.h.24.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
256
+ "transformer.h.24.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
257
+ "transformer.h.24.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
258
+ "transformer.h.24.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
259
+ "transformer.h.25.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
260
+ "transformer.h.25.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
261
+ "transformer.h.25.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
262
+ "transformer.h.25.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
263
+ "transformer.h.25.ln_1.bias": "pytorch_model-00002-of-00002.bin",
264
+ "transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00002.bin",
265
+ "transformer.h.25.ln_2.bias": "pytorch_model-00002-of-00002.bin",
266
+ "transformer.h.25.ln_2.weight": "pytorch_model-00002-of-00002.bin",
267
+ "transformer.h.25.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
268
+ "transformer.h.25.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
269
+ "transformer.h.25.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
270
+ "transformer.h.25.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
271
+ "transformer.h.25.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
272
+ "transformer.h.25.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
273
+ "transformer.h.26.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
274
+ "transformer.h.26.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
275
+ "transformer.h.26.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
276
+ "transformer.h.26.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
277
+ "transformer.h.26.ln_1.bias": "pytorch_model-00002-of-00002.bin",
278
+ "transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00002.bin",
279
+ "transformer.h.26.ln_2.bias": "pytorch_model-00002-of-00002.bin",
280
+ "transformer.h.26.ln_2.weight": "pytorch_model-00002-of-00002.bin",
281
+ "transformer.h.26.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
282
+ "transformer.h.26.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
283
+ "transformer.h.26.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
284
+ "transformer.h.26.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
285
+ "transformer.h.26.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
286
+ "transformer.h.26.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
287
+ "transformer.h.27.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
288
+ "transformer.h.27.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
289
+ "transformer.h.27.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
290
+ "transformer.h.27.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
291
+ "transformer.h.27.ln_1.bias": "pytorch_model-00002-of-00002.bin",
292
+ "transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00002.bin",
293
+ "transformer.h.27.ln_2.bias": "pytorch_model-00002-of-00002.bin",
294
+ "transformer.h.27.ln_2.weight": "pytorch_model-00002-of-00002.bin",
295
+ "transformer.h.27.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
296
+ "transformer.h.27.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
297
+ "transformer.h.27.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
298
+ "transformer.h.27.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
299
+ "transformer.h.27.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
300
+ "transformer.h.27.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
301
+ "transformer.h.28.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
302
+ "transformer.h.28.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
303
+ "transformer.h.28.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
304
+ "transformer.h.28.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
305
+ "transformer.h.28.ln_1.bias": "pytorch_model-00002-of-00002.bin",
306
+ "transformer.h.28.ln_1.weight": "pytorch_model-00002-of-00002.bin",
307
+ "transformer.h.28.ln_2.bias": "pytorch_model-00002-of-00002.bin",
308
+ "transformer.h.28.ln_2.weight": "pytorch_model-00002-of-00002.bin",
309
+ "transformer.h.28.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
310
+ "transformer.h.28.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
311
+ "transformer.h.28.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
312
+ "transformer.h.28.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
313
+ "transformer.h.28.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
314
+ "transformer.h.28.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
315
+ "transformer.h.29.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
316
+ "transformer.h.29.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
317
+ "transformer.h.29.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
318
+ "transformer.h.29.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
319
+ "transformer.h.29.ln_1.bias": "pytorch_model-00002-of-00002.bin",
320
+ "transformer.h.29.ln_1.weight": "pytorch_model-00002-of-00002.bin",
321
+ "transformer.h.29.ln_2.bias": "pytorch_model-00002-of-00002.bin",
322
+ "transformer.h.29.ln_2.weight": "pytorch_model-00002-of-00002.bin",
323
+ "transformer.h.29.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
324
+ "transformer.h.29.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
325
+ "transformer.h.29.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
326
+ "transformer.h.29.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
327
+ "transformer.h.29.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
328
+ "transformer.h.29.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
329
+ "transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
330
+ "transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
331
+ "transformer.h.3.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
332
+ "transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
333
+ "transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00002.bin",
334
+ "transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00002.bin",
335
+ "transformer.h.3.ln_2.bias": "pytorch_model-00001-of-00002.bin",
336
+ "transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00002.bin",
337
+ "transformer.h.3.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
338
+ "transformer.h.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
339
+ "transformer.h.3.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
340
+ "transformer.h.3.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
341
+ "transformer.h.3.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
342
+ "transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
343
+ "transformer.h.30.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
344
+ "transformer.h.30.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
345
+ "transformer.h.30.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
346
+ "transformer.h.30.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
347
+ "transformer.h.30.ln_1.bias": "pytorch_model-00002-of-00002.bin",
348
+ "transformer.h.30.ln_1.weight": "pytorch_model-00002-of-00002.bin",
349
+ "transformer.h.30.ln_2.bias": "pytorch_model-00002-of-00002.bin",
350
+ "transformer.h.30.ln_2.weight": "pytorch_model-00002-of-00002.bin",
351
+ "transformer.h.30.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
352
+ "transformer.h.30.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
353
+ "transformer.h.30.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
354
+ "transformer.h.30.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
355
+ "transformer.h.30.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
356
+ "transformer.h.30.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
357
+ "transformer.h.31.attn.c_attn.bias": "pytorch_model-00002-of-00002.bin",
358
+ "transformer.h.31.attn.c_attn.weight": "pytorch_model-00002-of-00002.bin",
359
+ "transformer.h.31.attn.c_proj.bias": "pytorch_model-00002-of-00002.bin",
360
+ "transformer.h.31.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
361
+ "transformer.h.31.ln_1.bias": "pytorch_model-00002-of-00002.bin",
362
+ "transformer.h.31.ln_1.weight": "pytorch_model-00002-of-00002.bin",
363
+ "transformer.h.31.ln_2.bias": "pytorch_model-00002-of-00002.bin",
364
+ "transformer.h.31.ln_2.weight": "pytorch_model-00002-of-00002.bin",
365
+ "transformer.h.31.mlp.c_fc.bias": "pytorch_model-00002-of-00002.bin",
366
+ "transformer.h.31.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
367
+ "transformer.h.31.mlp.c_fc2.bias": "pytorch_model-00002-of-00002.bin",
368
+ "transformer.h.31.mlp.c_fc2.weight": "pytorch_model-00002-of-00002.bin",
369
+ "transformer.h.31.mlp.c_proj.bias": "pytorch_model-00002-of-00002.bin",
370
+ "transformer.h.31.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
371
+ "transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
372
+ "transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
373
+ "transformer.h.4.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
374
+ "transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
375
+ "transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00002.bin",
376
+ "transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00002.bin",
377
+ "transformer.h.4.ln_2.bias": "pytorch_model-00001-of-00002.bin",
378
+ "transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00002.bin",
379
+ "transformer.h.4.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
380
+ "transformer.h.4.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
381
+ "transformer.h.4.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
382
+ "transformer.h.4.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
383
+ "transformer.h.4.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
384
+ "transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
385
+ "transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
386
+ "transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
387
+ "transformer.h.5.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
388
+ "transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
389
+ "transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00002.bin",
390
+ "transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00002.bin",
391
+ "transformer.h.5.ln_2.bias": "pytorch_model-00001-of-00002.bin",
392
+ "transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00002.bin",
393
+ "transformer.h.5.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
394
+ "transformer.h.5.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
395
+ "transformer.h.5.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
396
+ "transformer.h.5.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
397
+ "transformer.h.5.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
398
+ "transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
399
+ "transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
400
+ "transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
401
+ "transformer.h.6.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
402
+ "transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
403
+ "transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00002.bin",
404
+ "transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00002.bin",
405
+ "transformer.h.6.ln_2.bias": "pytorch_model-00001-of-00002.bin",
406
+ "transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00002.bin",
407
+ "transformer.h.6.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
408
+ "transformer.h.6.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
409
+ "transformer.h.6.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
410
+ "transformer.h.6.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
411
+ "transformer.h.6.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
412
+ "transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
413
+ "transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
414
+ "transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
415
+ "transformer.h.7.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
416
+ "transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
417
+ "transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00002.bin",
418
+ "transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00002.bin",
419
+ "transformer.h.7.ln_2.bias": "pytorch_model-00001-of-00002.bin",
420
+ "transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00002.bin",
421
+ "transformer.h.7.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
422
+ "transformer.h.7.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
423
+ "transformer.h.7.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
424
+ "transformer.h.7.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
425
+ "transformer.h.7.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
426
+ "transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
427
+ "transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
428
+ "transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
429
+ "transformer.h.8.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
430
+ "transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
431
+ "transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00002.bin",
432
+ "transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00002.bin",
433
+ "transformer.h.8.ln_2.bias": "pytorch_model-00001-of-00002.bin",
434
+ "transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00002.bin",
435
+ "transformer.h.8.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
436
+ "transformer.h.8.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
437
+ "transformer.h.8.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
438
+ "transformer.h.8.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
439
+ "transformer.h.8.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
440
+ "transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
441
+ "transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00002.bin",
442
+ "transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00002.bin",
443
+ "transformer.h.9.attn.c_proj.bias": "pytorch_model-00001-of-00002.bin",
444
+ "transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
445
+ "transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00002.bin",
446
+ "transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00002.bin",
447
+ "transformer.h.9.ln_2.bias": "pytorch_model-00001-of-00002.bin",
448
+ "transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00002.bin",
449
+ "transformer.h.9.mlp.c_fc.bias": "pytorch_model-00001-of-00002.bin",
450
+ "transformer.h.9.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
451
+ "transformer.h.9.mlp.c_fc2.bias": "pytorch_model-00001-of-00002.bin",
452
+ "transformer.h.9.mlp.c_fc2.weight": "pytorch_model-00001-of-00002.bin",
453
+ "transformer.h.9.mlp.c_proj.bias": "pytorch_model-00001-of-00002.bin",
454
+ "transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
455
+ "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
456
+ "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
457
+ "transformer.mm_projector.0.bias": "pytorch_model-00002-of-00002.bin",
458
+ "transformer.mm_projector.0.weight": "pytorch_model-00002-of-00002.bin",
459
+ "transformer.mm_projector.2.bias": "pytorch_model-00002-of-00002.bin",
460
+ "transformer.mm_projector.2.weight": "pytorch_model-00002-of-00002.bin",
461
+ "transformer.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "pytorch_model-00002-of-00002.bin",
462
+ "transformer.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "pytorch_model-00002-of-00002.bin",
463
+ "transformer.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "pytorch_model-00002-of-00002.bin",
464
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
465
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
466
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
467
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
468
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
469
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
470
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
471
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
472
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
473
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
474
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
475
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
476
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
477
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
478
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
479
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
480
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
481
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
482
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
483
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
484
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
485
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
486
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
487
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
488
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
489
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
490
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
491
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
492
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
493
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
494
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
495
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
496
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
497
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
498
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
499
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
500
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
501
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
502
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
503
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
504
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
505
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
506
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
507
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
508
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
509
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
510
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
511
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
512
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
513
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
514
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
515
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
516
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
517
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
518
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
519
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
520
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
521
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
522
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
523
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
524
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
525
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
526
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
527
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
528
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
529
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
530
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
531
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
532
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
533
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
534
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
535
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
536
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
537
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
538
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
539
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
540
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
541
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
542
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
543
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
544
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
545
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
546
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
547
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
548
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
549
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
550
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
551
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
552
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
553
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
554
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
555
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
556
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
557
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
558
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
559
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
560
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
561
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
562
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
563
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
564
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
565
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
566
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
567
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
568
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
569
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
570
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
571
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
572
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
573
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
574
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
575
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
576
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
577
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
578
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
579
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
580
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
581
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
582
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
583
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
584
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
585
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
586
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
587
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
588
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
589
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
590
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
591
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
592
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
593
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
594
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
595
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
596
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
597
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
598
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
599
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
600
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
601
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
602
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
603
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
604
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
605
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
606
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
607
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
608
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
609
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
610
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
611
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
612
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
613
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
614
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
615
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
616
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
617
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
618
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
619
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
620
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
621
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
622
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
623
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
624
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
625
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
626
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
627
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
628
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
629
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
630
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
631
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
632
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
633
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
634
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
635
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
636
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
637
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
638
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
639
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
640
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
641
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
642
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
643
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
644
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
645
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
646
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
647
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
648
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
649
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
650
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
651
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
652
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
653
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
654
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
655
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
656
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
657
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
658
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
659
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
660
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
661
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
662
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
663
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
664
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
665
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
666
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
667
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
668
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
669
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
670
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
671
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
672
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
673
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
674
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
675
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
676
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
677
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
678
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
679
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
680
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
681
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
682
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
683
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
684
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
685
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
686
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
687
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
688
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
689
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
690
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
691
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
692
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
693
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
694
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
695
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
696
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
697
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
698
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
699
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
700
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
701
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
702
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
703
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
704
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
705
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
706
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
707
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
708
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
709
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
710
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
711
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
712
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
713
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
714
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
715
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
716
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
717
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
718
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
719
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
720
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
721
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
722
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
723
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
724
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
725
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
726
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
727
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
728
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
729
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
730
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
731
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
732
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
733
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
734
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
735
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
736
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
737
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
738
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
739
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
740
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
741
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
742
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
743
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
744
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
745
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
746
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
747
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
748
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
749
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
750
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
751
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
752
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
753
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
754
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
755
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
756
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
757
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
758
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
759
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
760
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
761
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
762
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
763
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
764
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
765
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
766
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
767
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
768
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
769
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
770
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
771
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
772
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
773
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
774
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
775
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
776
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
777
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
778
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
779
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
780
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
781
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
782
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
783
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
784
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
785
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
786
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
787
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
788
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
789
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
790
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
791
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
792
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
793
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
794
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
795
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
796
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
797
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
798
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
799
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
800
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
801
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
802
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
803
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
804
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
805
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
806
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
807
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
808
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
809
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
810
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
811
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
812
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
813
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
814
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
815
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
816
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
817
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
818
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
819
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
820
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
821
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
822
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
823
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
824
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
825
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
826
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
827
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
828
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
829
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
830
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
831
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
832
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00002-of-00002.bin",
833
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00002-of-00002.bin",
834
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00002-of-00002.bin",
835
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00002-of-00002.bin",
836
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00002-of-00002.bin",
837
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00002-of-00002.bin",
838
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00002-of-00002.bin",
839
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00002-of-00002.bin",
840
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "pytorch_model-00002-of-00002.bin",
841
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
842
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "pytorch_model-00002-of-00002.bin",
843
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "pytorch_model-00002-of-00002.bin",
844
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "pytorch_model-00002-of-00002.bin",
845
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
846
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "pytorch_model-00002-of-00002.bin",
847
+ "transformer.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
848
+ "transformer.vision_tower.vision_tower.vision_model.post_layernorm.bias": "pytorch_model-00002-of-00002.bin",
849
+ "transformer.vision_tower.vision_tower.vision_model.post_layernorm.weight": "pytorch_model-00002-of-00002.bin",
850
+ "transformer.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "pytorch_model-00002-of-00002.bin",
851
+ "transformer.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "pytorch_model-00002-of-00002.bin",
852
+ "transformer.wte.weight": "pytorch_model-00001-of-00002.bin"
853
+ }
854
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "<|fim_prefix|>",
7
+ "<|fim_middle|>",
8
+ "<|fim_suffix|>",
9
+ "<|fim_pad|>",
10
+ "<|filename|>",
11
+ "<|gh_stars|>",
12
+ "<|issue_start|>",
13
+ "<|issue_comment|>",
14
+ "<|issue_closed|>",
15
+ "<|jupyter_start|>",
16
+ "<|jupyter_text|>",
17
+ "<|jupyter_code|>",
18
+ "<|jupyter_output|>",
19
+ "<|empty_output|>",
20
+ "<|commit_before|>",
21
+ "<|commit_msg|>",
22
+ "<|commit_after|>",
23
+ "<|reponame|>",
24
+ "<|im_start|>",
25
+ "<|im_end|>",
26
+ "<|sys_start|>",
27
+ "<|sys_end|>"
28
+ ],
29
+ "bos_token": "<s>",
30
+ "eos_token": "</s>",
31
+ "pad_token": "<unk>",
32
+ "unk_token": "<unk>"
33
+ }
tokenization_crystalcoder_fast.py ADDED
@@ -0,0 +1,144 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ import os
3
+ from shutil import copyfile
4
+ from typing import Optional, Tuple
5
+
6
+ from tokenizers import processors
7
+
8
+ from transformers.tokenization_utils_fast import PreTrainedTokenizerFast
9
+ from transformers.utils import is_sentencepiece_available, logging
10
+ from transformers.utils.versions import require_version
11
+
12
+
13
+ require_version("tokenizers>=0.13.3")
14
+
15
+
16
+
17
+ logger = logging.get_logger(__name__)
18
+ VOCAB_FILES_NAMES = {"vocab_file": "tokenizer.model", "tokenizer_file": "tokenizer.json"}
19
+
20
+ # fmt: off
21
+ DEFAULT_SYSTEM_PROMPT = """You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your \
22
+ answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure\
23
+ that your responses are socially unbiased and positive in nature.
24
+
25
+ If a question does not make any sense, or is not factually coherent, explain why instead of answering something not \
26
+ correct. If you don't know the answer to a question, please don't share false information."""
27
+ # fmt: on
28
+
29
+
30
+ class CrystalCoderTokenizerFast(PreTrainedTokenizerFast):
31
+
32
+
33
+ vocab_files_names = VOCAB_FILES_NAMES
34
+ slow_tokenizer_class = None
35
+ padding_side = "left"
36
+ model_input_names = ["input_ids", "attention_mask"]
37
+
38
+ def __init__(
39
+ self,
40
+ vocab_file=None,
41
+ tokenizer_file=None,
42
+ clean_up_tokenization_spaces=False,
43
+ unk_token="<|unk|>",
44
+ bos_token="<|startoftext|>",
45
+ eos_token="<|endoftext|>",
46
+ add_bos_token=False,
47
+ add_eos_token=False,
48
+ use_default_system_prompt=False,
49
+ **kwargs,
50
+ ):
51
+ super().__init__(
52
+ vocab_file=vocab_file,
53
+ tokenizer_file=tokenizer_file,
54
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
55
+ unk_token=unk_token,
56
+ bos_token=bos_token,
57
+ eos_token=eos_token,
58
+ use_default_system_prompt=use_default_system_prompt,
59
+ **kwargs,
60
+ )
61
+ self._add_bos_token = add_bos_token
62
+ self._add_eos_token = add_eos_token
63
+ self.update_post_processor()
64
+ self.use_default_system_prompt = use_default_system_prompt
65
+ self.vocab_file = vocab_file
66
+
67
+ @property
68
+ def can_save_slow_tokenizer(self) -> bool:
69
+ return os.path.isfile(self.vocab_file) if self.vocab_file else False
70
+
71
+ def update_post_processor(self):
72
+ """
73
+ Updates the underlying post processor with the current `bos_token` and `eos_token`.
74
+ """
75
+ bos = self.bos_token
76
+ bos_token_id = self.bos_token_id
77
+ if bos is None and self.add_bos_token:
78
+ raise ValueError("add_bos_token = True but bos_token = None")
79
+
80
+ eos = self.eos_token
81
+ eos_token_id = self.eos_token_id
82
+ if eos is None and self.add_eos_token:
83
+ raise ValueError("add_eos_token = True but eos_token = None")
84
+
85
+ single = f"{(bos+':0 ') if self.add_bos_token else ''}$A:0{(' '+eos+':0') if self.add_eos_token else ''}"
86
+ pair = f"{single}{(' '+bos+':1') if self.add_bos_token else ''} $B:1{(' '+eos+':1') if self.add_eos_token else ''}"
87
+
88
+ special_tokens = []
89
+ if self.add_bos_token:
90
+ special_tokens.append((bos, bos_token_id))
91
+ if self.add_eos_token:
92
+ special_tokens.append((eos, eos_token_id))
93
+ self._tokenizer.post_processor = processors.TemplateProcessing(
94
+ single=single, pair=pair, special_tokens=special_tokens
95
+ )
96
+
97
+ @property
98
+ def add_eos_token(self):
99
+ return self._add_eos_token
100
+
101
+ @property
102
+ def add_bos_token(self):
103
+ return self._add_bos_token
104
+
105
+ @add_eos_token.setter
106
+ def add_eos_token(self, value):
107
+ self._add_eos_token = value
108
+ self.update_post_processor()
109
+
110
+ @add_bos_token.setter
111
+ def add_bos_token(self, value):
112
+ self._add_bos_token = value
113
+ self.update_post_processor()
114
+
115
+ def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
116
+ if not self.can_save_slow_tokenizer:
117
+ raise ValueError(
118
+ "Your fast tokenizer does not have the necessary information to save the vocabulary for a slow "
119
+ "tokenizer."
120
+ )
121
+
122
+ if not os.path.isdir(save_directory):
123
+ logger.error(f"Vocabulary path ({save_directory}) should be a directory")
124
+ return
125
+ out_vocab_file = os.path.join(
126
+ save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
127
+ )
128
+
129
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file):
130
+ copyfile(self.vocab_file, out_vocab_file)
131
+
132
+ return (out_vocab_file,)
133
+
134
+
135
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
136
+ bos_token_id = [self.bos_token_id] if self.add_bos_token else []
137
+ eos_token_id = [self.eos_token_id] if self.add_eos_token else []
138
+
139
+ output = bos_token_id + token_ids_0 + eos_token_id
140
+
141
+ if token_ids_1 is not None:
142
+ output = output + bos_token_id + token_ids_1 + eos_token_id
143
+
144
+ return output
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,269 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<|fim_prefix|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<|fim_middle|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32002": {
44
+ "content": "<|fim_suffix|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32003": {
52
+ "content": "<|fim_pad|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "32004": {
60
+ "content": "<|filename|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "32005": {
68
+ "content": "<|gh_stars|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "32006": {
76
+ "content": "<|issue_start|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "32007": {
84
+ "content": "<|issue_comment|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "32008": {
92
+ "content": "<|issue_closed|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "32009": {
100
+ "content": "<|jupyter_start|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "32010": {
108
+ "content": "<|jupyter_text|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "32011": {
116
+ "content": "<|jupyter_code|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "32012": {
124
+ "content": "<|jupyter_output|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "32013": {
132
+ "content": "<|empty_output|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "32014": {
140
+ "content": "<|commit_before|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "32015": {
148
+ "content": "<|commit_msg|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "32016": {
156
+ "content": "<|commit_after|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "32017": {
164
+ "content": "<|reponame|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "32018": {
172
+ "content": "<|im_start|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "32019": {
180
+ "content": "<|im_end|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "32020": {
188
+ "content": "<|sys_start|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "32021": {
196
+ "content": "<|sys_end|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ }
203
+ },
204
+ "additional_special_tokens": [
205
+ "<unk>",
206
+ "<s>",
207
+ "</s>",
208
+ "<|fim_prefix|>",
209
+ "<|fim_middle|>",
210
+ "<|fim_suffix|>",
211
+ "<|fim_pad|>",
212
+ "<|filename|>",
213
+ "<|gh_stars|>",
214
+ "<|issue_start|>",
215
+ "<|issue_comment|>",
216
+ "<|issue_closed|>",
217
+ "<|jupyter_start|>",
218
+ "<|jupyter_text|>",
219
+ "<|jupyter_code|>",
220
+ "<|jupyter_output|>",
221
+ "<|empty_output|>",
222
+ "<|commit_before|>",
223
+ "<|commit_msg|>",
224
+ "<|commit_after|>",
225
+ "<|reponame|>",
226
+ "<|im_start|>",
227
+ "<|im_end|>",
228
+ "<|sys_start|>",
229
+ "<|sys_end|>"
230
+ ],
231
+ "auto_map": {
232
+ "AutoTokenizer": [
233
+ null,
234
+ "tokenization_crystalcoder_fast.CrystalCoderTokenizerFast"
235
+ ]
236
+ },
237
+ "bos_token": {
238
+ "__type": "AddedToken",
239
+ "content": "</s>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false
244
+ },
245
+ "clean_up_tokenization_spaces": false,
246
+ "eos_token": {
247
+ "__type": "AddedToken",
248
+ "content": "</s>",
249
+ "lstrip": false,
250
+ "normalized": false,
251
+ "rstrip": false,
252
+ "single_word": false
253
+ },
254
+ "legacy": false,
255
+ "model_max_length": 2048,
256
+ "pad_token": null,
257
+ "padding_side": "right",
258
+ "sp_model_kwargs": {},
259
+ "tokenizer_class": "CrystalCoderTokenizer",
260
+ "unk_token": {
261
+ "__type": "AddedToken",
262
+ "content": "<unk>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false
267
+ },
268
+ "use_default_system_prompt": false
269
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c91416669914faf32b8361aca767d170cdb6c1a55e5cec000594812c2a6a6be
3
+ size 6139