Hugging Face's logo

OpenGVLab
/
InternVL-Chat-V1-1

Visual Question Answering
Transformers
PyTorch
internvl_chat
feature-extraction
custom_code
Model card Files Community
1
czczup commited on
Commit
01eb2ce
•
1 Parent(s): da95d72

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. added_tokens.json +15 -0
  2. config.json +178 -0
  3. pytorch_model-00001-of-00004.bin +3 -0
  4. pytorch_model-00002-of-00004.bin +3 -0
  5. pytorch_model-00003-of-00004.bin +3 -0
  6. pytorch_model-00004-of-00004.bin +3 -0
  7. pytorch_model.bin.index.json +1004 -0
  8. special_tokens_map.json +96 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +163 -0
added_tokens.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 41913,
3
+ "</img>": 41909,
4
+ "</quad>": 41918,
5
+ "</ref>": 41915,
6
+ "</vid>": 41911,
7
+ "<IMG_CONTEXT>": 41916,
8
+ "<bot>": 41907,
9
+ "<box>": 41912,
10
+ "<human>": 41906,
11
+ "<img>": 41908,
12
+ "<quad>": 41917,
13
+ "<ref>": 41914,
14
+ "<vid>": 41910
15
+ }
config.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "downsample_ratio": 0.5,
8
+ "force_image_size": 448,
9
+ "llm_config": {
10
+ "add_cross_attention": false,
11
+ "architectures": [
12
+ "LlamaForCausalLM"
13
+ ],
14
+ "attention_bias": false,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": 1,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 2,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "hidden_act": "silu",
31
+ "hidden_size": 5120,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 13824,
38
+ "is_decoder": false,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
+ "length_penalty": 1.0,
45
+ "max_length": 20,
46
+ "max_position_embeddings": 4096,
47
+ "min_length": 0,
48
+ "model_type": "llama",
49
+ "no_repeat_ngram_size": 0,
50
+ "num_attention_heads": 40,
51
+ "num_beam_groups": 1,
52
+ "num_beams": 1,
53
+ "num_hidden_layers": 40,
54
+ "num_key_value_heads": 40,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": null,
60
+ "prefix": null,
61
+ "pretraining_tp": 1,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "rms_norm_eps": 1e-05,
69
+ "rope_scaling": null,
70
+ "rope_theta": 10000.0,
71
+ "sep_token_id": null,
72
+ "suppress_tokens": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tf_legacy_loss": false,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": false,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": "bfloat16",
82
+ "torchscript": false,
83
+ "transformers_version": "4.32.0",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "use_cache": false,
87
+ "vocab_size": 41919
88
+ },
89
+ "model_type": "internvl_chat",
90
+ "pad2square": false,
91
+ "select_layer": -4,
92
+ "template": "internvl_zh",
93
+ "torch_dtype": "bfloat16",
94
+ "transformers_version": "4.32.0",
95
+ "use_backbone_lora": 0,
96
+ "use_llm_lora": 0,
97
+ "vision_config": {
98
+ "_name_or_path": "",
99
+ "add_cross_attention": false,
100
+ "architectures": null,
101
+ "attention_dropout": 0.0,
102
+ "bad_words_ids": null,
103
+ "begin_suppress_tokens": null,
104
+ "bos_token_id": null,
105
+ "chunk_size_feed_forward": 0,
106
+ "cross_attention_hidden_size": null,
107
+ "decoder_start_token_id": null,
108
+ "diversity_penalty": 0.0,
109
+ "do_sample": false,
110
+ "drop_path_rate": 0.0,
111
+ "dropout": 0.0,
112
+ "early_stopping": false,
113
+ "encoder_no_repeat_ngram_size": 0,
114
+ "eos_token_id": null,
115
+ "exponential_decay_length_penalty": null,
116
+ "finetuning_task": null,
117
+ "forced_bos_token_id": null,
118
+ "forced_eos_token_id": null,
119
+ "hidden_act": "gelu",
120
+ "hidden_size": 3200,
121
+ "id2label": {
122
+ "0": "LABEL_0",
123
+ "1": "LABEL_1"
124
+ },
125
+ "image_size": 224,
126
+ "initializer_factor": 0.1,
127
+ "initializer_range": 1e-10,
128
+ "intermediate_size": 12800,
129
+ "is_decoder": false,
130
+ "is_encoder_decoder": false,
131
+ "label2id": {
132
+ "LABEL_0": 0,
133
+ "LABEL_1": 1
134
+ },
135
+ "layer_norm_eps": 1e-06,
136
+ "length_penalty": 1.0,
137
+ "max_length": 20,
138
+ "min_length": 0,
139
+ "model_type": "intern_vit_6b",
140
+ "no_repeat_ngram_size": 0,
141
+ "num_attention_heads": 25,
142
+ "num_beam_groups": 1,
143
+ "num_beams": 1,
144
+ "num_channels": 3,
145
+ "num_hidden_layers": 48,
146
+ "num_return_sequences": 1,
147
+ "output_attentions": false,
148
+ "output_hidden_states": false,
149
+ "output_scores": false,
150
+ "pad_token_id": null,
151
+ "patch_size": 14,
152
+ "prefix": null,
153
+ "problem_type": null,
154
+ "pruned_heads": {},
155
+ "qk_normalization": true,
156
+ "qkv_bias": false,
157
+ "remove_invalid_values": false,
158
+ "repetition_penalty": 1.0,
159
+ "return_dict": true,
160
+ "return_dict_in_generate": false,
161
+ "sep_token_id": null,
162
+ "suppress_tokens": null,
163
+ "task_specific_params": null,
164
+ "temperature": 1.0,
165
+ "tf_legacy_loss": false,
166
+ "tie_encoder_decoder": false,
167
+ "tie_word_embeddings": true,
168
+ "tokenizer_class": null,
169
+ "top_k": 50,
170
+ "top_p": 1.0,
171
+ "torch_dtype": null,
172
+ "torchscript": false,
173
+ "transformers_version": "4.32.0",
174
+ "typical_p": 1.0,
175
+ "use_bfloat16": true,
176
+ "use_flash_attn": true
177
+ }
178
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8383cc695760cf6ae0cc7108b5c7471011ee5c32c4eb27a3312d9f938214476
3
+ size 9925944248
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a88caccb8f0a855b27ca28cafce72066ae6aca05705b1a2bb1ffe40d009ca73c
3
+ size 9979402692
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0dd1ac5dff8fbc125940bb89369c00cd2e316753a5fda91c8d4dcc43d07fbf9
3
+ size 9956586659
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee8d0fb9a6aaf17cd41e4f34dad391aba6893f20bbac6b786eefd62e49009366
3
+ size 8367361208
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,1004 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 38228944640
4
+ },
5
+ "weight_map": {
6
+ "language_model.lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "language_model.model.embed_tokens.weight": "pytorch_model-00002-of-00004.bin",
8
+ "language_model.model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
9
+ "language_model.model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
10
+ "language_model.model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
11
+ "language_model.model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
12
+ "language_model.model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
13
+ "language_model.model.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
14
+ "language_model.model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
15
+ "language_model.model.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
16
+ "language_model.model.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
17
+ "language_model.model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
18
+ "language_model.model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
19
+ "language_model.model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
20
+ "language_model.model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
21
+ "language_model.model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
22
+ "language_model.model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
23
+ "language_model.model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
24
+ "language_model.model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
25
+ "language_model.model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
26
+ "language_model.model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
27
+ "language_model.model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
28
+ "language_model.model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
29
+ "language_model.model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
30
+ "language_model.model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
31
+ "language_model.model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
32
+ "language_model.model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
33
+ "language_model.model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
34
+ "language_model.model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
35
+ "language_model.model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
36
+ "language_model.model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
37
+ "language_model.model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
38
+ "language_model.model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
39
+ "language_model.model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
40
+ "language_model.model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
41
+ "language_model.model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
42
+ "language_model.model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
43
+ "language_model.model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
44
+ "language_model.model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
45
+ "language_model.model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
46
+ "language_model.model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
47
+ "language_model.model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
48
+ "language_model.model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
49
+ "language_model.model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
50
+ "language_model.model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
51
+ "language_model.model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
52
+ "language_model.model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
53
+ "language_model.model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
54
+ "language_model.model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
55
+ "language_model.model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
56
+ "language_model.model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
57
+ "language_model.model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
58
+ "language_model.model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
59
+ "language_model.model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
60
+ "language_model.model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
61
+ "language_model.model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
62
+ "language_model.model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
63
+ "language_model.model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
64
+ "language_model.model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
65
+ "language_model.model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
66
+ "language_model.model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
67
+ "language_model.model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
68
+ "language_model.model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
69
+ "language_model.model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
70
+ "language_model.model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
71
+ "language_model.model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
72
+ "language_model.model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
73
+ "language_model.model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
74
+ "language_model.model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
75
+ "language_model.model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
76
+ "language_model.model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
77
+ "language_model.model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
78
+ "language_model.model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
79
+ "language_model.model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
80
+ "language_model.model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
81
+ "language_model.model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
82
+ "language_model.model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
83
+ "language_model.model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
84
+ "language_model.model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
85
+ "language_model.model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
86
+ "language_model.model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
87
+ "language_model.model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
88
+ "language_model.model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
89
+ "language_model.model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
90
+ "language_model.model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
91
+ "language_model.model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
92
+ "language_model.model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
93
+ "language_model.model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
94
+ "language_model.model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
95
+ "language_model.model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
96
+ "language_model.model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
97
+ "language_model.model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
98
+ "language_model.model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
99
+ "language_model.model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
100
+ "language_model.model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
101
+ "language_model.model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
102
+ "language_model.model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
103
+ "language_model.model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
104
+ "language_model.model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
105
+ "language_model.model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
106
+ "language_model.model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
107
+ "language_model.model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
108
+ "language_model.model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
109
+ "language_model.model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
110
+ "language_model.model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
111
+ "language_model.model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
112
+ "language_model.model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
113
+ "language_model.model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
114
+ "language_model.model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
115
+ "language_model.model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
116
+ "language_model.model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
117
+ "language_model.model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
118
+ "language_model.model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
119
+ "language_model.model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
120
+ "language_model.model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
121
+ "language_model.model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
122
+ "language_model.model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
123
+ "language_model.model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
124
+ "language_model.model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
125
+ "language_model.model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
126
+ "language_model.model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
127
+ "language_model.model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
128
+ "language_model.model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
129
+ "language_model.model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
130
+ "language_model.model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
131
+ "language_model.model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
132
+ "language_model.model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
133
+ "language_model.model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
134
+ "language_model.model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
135
+ "language_model.model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
136
+ "language_model.model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
137
+ "language_model.model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
138
+ "language_model.model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
139
+ "language_model.model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
140
+ "language_model.model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
141
+ "language_model.model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
142
+ "language_model.model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
143
+ "language_model.model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
144
+ "language_model.model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
145
+ "language_model.model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
146
+ "language_model.model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
147
+ "language_model.model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
148
+ "language_model.model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
149
+ "language_model.model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
150
+ "language_model.model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
151
+ "language_model.model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
152
+ "language_model.model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
153
+ "language_model.model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
154
+ "language_model.model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
155
+ "language_model.model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
156
+ "language_model.model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
157
+ "language_model.model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
158
+ "language_model.model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
159
+ "language_model.model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
160
+ "language_model.model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
161
+ "language_model.model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
162
+ "language_model.model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
163
+ "language_model.model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
164
+ "language_model.model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
165
+ "language_model.model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
166
+ "language_model.model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
167
+ "language_model.model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
168
+ "language_model.model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
169
+ "language_model.model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
170
+ "language_model.model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
171
+ "language_model.model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
172
+ "language_model.model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
173
+ "language_model.model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
174
+ "language_model.model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
175
+ "language_model.model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
176
+ "language_model.model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
177
+ "language_model.model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
178
+ "language_model.model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
179
+ "language_model.model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
180
+ "language_model.model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
181
+ "language_model.model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
182
+ "language_model.model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
183
+ "language_model.model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
184
+ "language_model.model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
185
+ "language_model.model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
186
+ "language_model.model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
187
+ "language_model.model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
188
+ "language_model.model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
189
+ "language_model.model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
190
+ "language_model.model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
191
+ "language_model.model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
192
+ "language_model.model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
193
+ "language_model.model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
194
+ "language_model.model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
195
+ "language_model.model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
196
+ "language_model.model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
197
+ "language_model.model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
198
+ "language_model.model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
199
+ "language_model.model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
200
+ "language_model.model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
201
+ "language_model.model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
202
+ "language_model.model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
203
+ "language_model.model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
204
+ "language_model.model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
205
+ "language_model.model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
206
+ "language_model.model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
207
+ "language_model.model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
208
+ "language_model.model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
209
+ "language_model.model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
210
+ "language_model.model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
211
+ "language_model.model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
212
+ "language_model.model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
213
+ "language_model.model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
214
+ "language_model.model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
215
+ "language_model.model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
216
+ "language_model.model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
217
+ "language_model.model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
218
+ "language_model.model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
219
+ "language_model.model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
220
+ "language_model.model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
221
+ "language_model.model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
222
+ "language_model.model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
223
+ "language_model.model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
224
+ "language_model.model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
225
+ "language_model.model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
226
+ "language_model.model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
227
+ "language_model.model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
228
+ "language_model.model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
229
+ "language_model.model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
230
+ "language_model.model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
231
+ "language_model.model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
232
+ "language_model.model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
233
+ "language_model.model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
234
+ "language_model.model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
235
+ "language_model.model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
236
+ "language_model.model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
237
+ "language_model.model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
238
+ "language_model.model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
239
+ "language_model.model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
240
+ "language_model.model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
241
+ "language_model.model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
242
+ "language_model.model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
243
+ "language_model.model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
244
+ "language_model.model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
245
+ "language_model.model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
246
+ "language_model.model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
247
+ "language_model.model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
248
+ "language_model.model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
249
+ "language_model.model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
250
+ "language_model.model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
251
+ "language_model.model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
252
+ "language_model.model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
253
+ "language_model.model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
254
+ "language_model.model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
255
+ "language_model.model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
256
+ "language_model.model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
257
+ "language_model.model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
258
+ "language_model.model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
259
+ "language_model.model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
260
+ "language_model.model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
261
+ "language_model.model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
262
+ "language_model.model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
263
+ "language_model.model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
264
+ "language_model.model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
265
+ "language_model.model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
266
+ "language_model.model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
267
+ "language_model.model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
268
+ "language_model.model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
269
+ "language_model.model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
270
+ "language_model.model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
271
+ "language_model.model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
272
+ "language_model.model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
273
+ "language_model.model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
274
+ "language_model.model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
275
+ "language_model.model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
276
+ "language_model.model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
277
+ "language_model.model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
278
+ "language_model.model.layers.36.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
279
+ "language_model.model.layers.36.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
280
+ "language_model.model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
281
+ "language_model.model.layers.36.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
282
+ "language_model.model.layers.36.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
283
+ "language_model.model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
284
+ "language_model.model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
285
+ "language_model.model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
286
+ "language_model.model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
287
+ "language_model.model.layers.37.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
288
+ "language_model.model.layers.37.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
289
+ "language_model.model.layers.37.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
290
+ "language_model.model.layers.37.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
291
+ "language_model.model.layers.37.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
292
+ "language_model.model.layers.37.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
293
+ "language_model.model.layers.37.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
294
+ "language_model.model.layers.37.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
295
+ "language_model.model.layers.37.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
296
+ "language_model.model.layers.38.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
297
+ "language_model.model.layers.38.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
298
+ "language_model.model.layers.38.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
299
+ "language_model.model.layers.38.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
300
+ "language_model.model.layers.38.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
301
+ "language_model.model.layers.38.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
302
+ "language_model.model.layers.38.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
303
+ "language_model.model.layers.38.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
304
+ "language_model.model.layers.38.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
305
+ "language_model.model.layers.39.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
306
+ "language_model.model.layers.39.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
307
+ "language_model.model.layers.39.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
308
+ "language_model.model.layers.39.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
309
+ "language_model.model.layers.39.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
310
+ "language_model.model.layers.39.self_attn.k_proj.weight": "pytorch_model-00004-of-00004.bin",
311
+ "language_model.model.layers.39.self_attn.o_proj.weight": "pytorch_model-00004-of-00004.bin",
312
+ "language_model.model.layers.39.self_attn.q_proj.weight": "pytorch_model-00004-of-00004.bin",
313
+ "language_model.model.layers.39.self_attn.v_proj.weight": "pytorch_model-00004-of-00004.bin",
314
+ "language_model.model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
315
+ "language_model.model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
316
+ "language_model.model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
317
+ "language_model.model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
318
+ "language_model.model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
319
+ "language_model.model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
320
+ "language_model.model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
321
+ "language_model.model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
322
+ "language_model.model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
323
+ "language_model.model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
324
+ "language_model.model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
325
+ "language_model.model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
326
+ "language_model.model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
327
+ "language_model.model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
328
+ "language_model.model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
329
+ "language_model.model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
330
+ "language_model.model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
331
+ "language_model.model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
332
+ "language_model.model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
333
+ "language_model.model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
334
+ "language_model.model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
335
+ "language_model.model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
336
+ "language_model.model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
337
+ "language_model.model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
338
+ "language_model.model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
339
+ "language_model.model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
340
+ "language_model.model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
341
+ "language_model.model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
342
+ "language_model.model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
343
+ "language_model.model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
344
+ "language_model.model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
345
+ "language_model.model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
346
+ "language_model.model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
347
+ "language_model.model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
348
+ "language_model.model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
349
+ "language_model.model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
350
+ "language_model.model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
351
+ "language_model.model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
352
+ "language_model.model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
353
+ "language_model.model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
354
+ "language_model.model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
355
+ "language_model.model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
356
+ "language_model.model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
357
+ "language_model.model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
358
+ "language_model.model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
359
+ "language_model.model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
360
+ "language_model.model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
361
+ "language_model.model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
362
+ "language_model.model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
363
+ "language_model.model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
364
+ "language_model.model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
365
+ "language_model.model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
366
+ "language_model.model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
367
+ "language_model.model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
368
+ "language_model.model.norm.weight": "pytorch_model-00004-of-00004.bin",
369
+ "mlp1.0.bias": "pytorch_model-00004-of-00004.bin",
370
+ "mlp1.0.weight": "pytorch_model-00004-of-00004.bin",
371
+ "mlp1.1.bias": "pytorch_model-00004-of-00004.bin",
372
+ "mlp1.1.weight": "pytorch_model-00004-of-00004.bin",
373
+ "mlp1.3.bias": "pytorch_model-00004-of-00004.bin",
374
+ "mlp1.3.weight": "pytorch_model-00004-of-00004.bin",
375
+ "vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00004.bin",
376
+ "vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00004.bin",
377
+ "vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00004.bin",
378
+ "vision_model.embeddings.position_embedding": "pytorch_model-00001-of-00004.bin",
379
+ "vision_model.encoder.layers.0.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
380
+ "vision_model.encoder.layers.0.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
381
+ "vision_model.encoder.layers.0.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
382
+ "vision_model.encoder.layers.0.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
383
+ "vision_model.encoder.layers.0.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
384
+ "vision_model.encoder.layers.0.ls1": "pytorch_model-00001-of-00004.bin",
385
+ "vision_model.encoder.layers.0.ls2": "pytorch_model-00001-of-00004.bin",
386
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
387
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
388
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
389
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
390
+ "vision_model.encoder.layers.0.norm1.weight": "pytorch_model-00001-of-00004.bin",
391
+ "vision_model.encoder.layers.0.norm2.weight": "pytorch_model-00001-of-00004.bin",
392
+ "vision_model.encoder.layers.1.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
393
+ "vision_model.encoder.layers.1.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
394
+ "vision_model.encoder.layers.1.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
395
+ "vision_model.encoder.layers.1.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
396
+ "vision_model.encoder.layers.1.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
397
+ "vision_model.encoder.layers.1.ls1": "pytorch_model-00001-of-00004.bin",
398
+ "vision_model.encoder.layers.1.ls2": "pytorch_model-00001-of-00004.bin",
399
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
400
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
401
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
402
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
403
+ "vision_model.encoder.layers.1.norm1.weight": "pytorch_model-00001-of-00004.bin",
404
+ "vision_model.encoder.layers.1.norm2.weight": "pytorch_model-00001-of-00004.bin",
405
+ "vision_model.encoder.layers.10.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
406
+ "vision_model.encoder.layers.10.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
407
+ "vision_model.encoder.layers.10.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
408
+ "vision_model.encoder.layers.10.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
409
+ "vision_model.encoder.layers.10.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
410
+ "vision_model.encoder.layers.10.ls1": "pytorch_model-00001-of-00004.bin",
411
+ "vision_model.encoder.layers.10.ls2": "pytorch_model-00001-of-00004.bin",
412
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
413
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
414
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
415
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
416
+ "vision_model.encoder.layers.10.norm1.weight": "pytorch_model-00001-of-00004.bin",
417
+ "vision_model.encoder.layers.10.norm2.weight": "pytorch_model-00001-of-00004.bin",
418
+ "vision_model.encoder.layers.11.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
419
+ "vision_model.encoder.layers.11.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
420
+ "vision_model.encoder.layers.11.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
421
+ "vision_model.encoder.layers.11.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
422
+ "vision_model.encoder.layers.11.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
423
+ "vision_model.encoder.layers.11.ls1": "pytorch_model-00001-of-00004.bin",
424
+ "vision_model.encoder.layers.11.ls2": "pytorch_model-00001-of-00004.bin",
425
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
426
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
427
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
428
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
429
+ "vision_model.encoder.layers.11.norm1.weight": "pytorch_model-00001-of-00004.bin",
430
+ "vision_model.encoder.layers.11.norm2.weight": "pytorch_model-00001-of-00004.bin",
431
+ "vision_model.encoder.layers.12.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
432
+ "vision_model.encoder.layers.12.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
433
+ "vision_model.encoder.layers.12.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
434
+ "vision_model.encoder.layers.12.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
435
+ "vision_model.encoder.layers.12.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
436
+ "vision_model.encoder.layers.12.ls1": "pytorch_model-00001-of-00004.bin",
437
+ "vision_model.encoder.layers.12.ls2": "pytorch_model-00001-of-00004.bin",
438
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
439
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
440
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
441
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
442
+ "vision_model.encoder.layers.12.norm1.weight": "pytorch_model-00001-of-00004.bin",
443
+ "vision_model.encoder.layers.12.norm2.weight": "pytorch_model-00001-of-00004.bin",
444
+ "vision_model.encoder.layers.13.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
445
+ "vision_model.encoder.layers.13.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
446
+ "vision_model.encoder.layers.13.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
447
+ "vision_model.encoder.layers.13.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
448
+ "vision_model.encoder.layers.13.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
449
+ "vision_model.encoder.layers.13.ls1": "pytorch_model-00001-of-00004.bin",
450
+ "vision_model.encoder.layers.13.ls2": "pytorch_model-00001-of-00004.bin",
451
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
452
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
453
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
454
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
455
+ "vision_model.encoder.layers.13.norm1.weight": "pytorch_model-00001-of-00004.bin",
456
+ "vision_model.encoder.layers.13.norm2.weight": "pytorch_model-00001-of-00004.bin",
457
+ "vision_model.encoder.layers.14.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
458
+ "vision_model.encoder.layers.14.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
459
+ "vision_model.encoder.layers.14.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
460
+ "vision_model.encoder.layers.14.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
461
+ "vision_model.encoder.layers.14.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
462
+ "vision_model.encoder.layers.14.ls1": "pytorch_model-00001-of-00004.bin",
463
+ "vision_model.encoder.layers.14.ls2": "pytorch_model-00001-of-00004.bin",
464
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
465
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
466
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
467
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
468
+ "vision_model.encoder.layers.14.norm1.weight": "pytorch_model-00001-of-00004.bin",
469
+ "vision_model.encoder.layers.14.norm2.weight": "pytorch_model-00001-of-00004.bin",
470
+ "vision_model.encoder.layers.15.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
471
+ "vision_model.encoder.layers.15.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
472
+ "vision_model.encoder.layers.15.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
473
+ "vision_model.encoder.layers.15.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
474
+ "vision_model.encoder.layers.15.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
475
+ "vision_model.encoder.layers.15.ls1": "pytorch_model-00001-of-00004.bin",
476
+ "vision_model.encoder.layers.15.ls2": "pytorch_model-00001-of-00004.bin",
477
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
478
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
479
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
480
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
481
+ "vision_model.encoder.layers.15.norm1.weight": "pytorch_model-00001-of-00004.bin",
482
+ "vision_model.encoder.layers.15.norm2.weight": "pytorch_model-00001-of-00004.bin",
483
+ "vision_model.encoder.layers.16.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
484
+ "vision_model.encoder.layers.16.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
485
+ "vision_model.encoder.layers.16.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
486
+ "vision_model.encoder.layers.16.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
487
+ "vision_model.encoder.layers.16.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
488
+ "vision_model.encoder.layers.16.ls1": "pytorch_model-00001-of-00004.bin",
489
+ "vision_model.encoder.layers.16.ls2": "pytorch_model-00001-of-00004.bin",
490
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
491
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
492
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
493
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
494
+ "vision_model.encoder.layers.16.norm1.weight": "pytorch_model-00001-of-00004.bin",
495
+ "vision_model.encoder.layers.16.norm2.weight": "pytorch_model-00001-of-00004.bin",
496
+ "vision_model.encoder.layers.17.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
497
+ "vision_model.encoder.layers.17.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
498
+ "vision_model.encoder.layers.17.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
499
+ "vision_model.encoder.layers.17.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
500
+ "vision_model.encoder.layers.17.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
501
+ "vision_model.encoder.layers.17.ls1": "pytorch_model-00001-of-00004.bin",
502
+ "vision_model.encoder.layers.17.ls2": "pytorch_model-00001-of-00004.bin",
503
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
504
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
505
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
506
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
507
+ "vision_model.encoder.layers.17.norm1.weight": "pytorch_model-00001-of-00004.bin",
508
+ "vision_model.encoder.layers.17.norm2.weight": "pytorch_model-00001-of-00004.bin",
509
+ "vision_model.encoder.layers.18.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
510
+ "vision_model.encoder.layers.18.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
511
+ "vision_model.encoder.layers.18.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
512
+ "vision_model.encoder.layers.18.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
513
+ "vision_model.encoder.layers.18.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
514
+ "vision_model.encoder.layers.18.ls1": "pytorch_model-00001-of-00004.bin",
515
+ "vision_model.encoder.layers.18.ls2": "pytorch_model-00001-of-00004.bin",
516
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
517
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
518
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
519
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
520
+ "vision_model.encoder.layers.18.norm1.weight": "pytorch_model-00001-of-00004.bin",
521
+ "vision_model.encoder.layers.18.norm2.weight": "pytorch_model-00001-of-00004.bin",
522
+ "vision_model.encoder.layers.19.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
523
+ "vision_model.encoder.layers.19.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
524
+ "vision_model.encoder.layers.19.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
525
+ "vision_model.encoder.layers.19.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
526
+ "vision_model.encoder.layers.19.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
527
+ "vision_model.encoder.layers.19.ls1": "pytorch_model-00001-of-00004.bin",
528
+ "vision_model.encoder.layers.19.ls2": "pytorch_model-00001-of-00004.bin",
529
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
530
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
531
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
532
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
533
+ "vision_model.encoder.layers.19.norm1.weight": "pytorch_model-00001-of-00004.bin",
534
+ "vision_model.encoder.layers.19.norm2.weight": "pytorch_model-00001-of-00004.bin",
535
+ "vision_model.encoder.layers.2.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
536
+ "vision_model.encoder.layers.2.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
537
+ "vision_model.encoder.layers.2.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
538
+ "vision_model.encoder.layers.2.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
539
+ "vision_model.encoder.layers.2.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
540
+ "vision_model.encoder.layers.2.ls1": "pytorch_model-00001-of-00004.bin",
541
+ "vision_model.encoder.layers.2.ls2": "pytorch_model-00001-of-00004.bin",
542
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
543
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
544
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
545
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
546
+ "vision_model.encoder.layers.2.norm1.weight": "pytorch_model-00001-of-00004.bin",
547
+ "vision_model.encoder.layers.2.norm2.weight": "pytorch_model-00001-of-00004.bin",
548
+ "vision_model.encoder.layers.20.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
549
+ "vision_model.encoder.layers.20.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
550
+ "vision_model.encoder.layers.20.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
551
+ "vision_model.encoder.layers.20.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
552
+ "vision_model.encoder.layers.20.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
553
+ "vision_model.encoder.layers.20.ls1": "pytorch_model-00001-of-00004.bin",
554
+ "vision_model.encoder.layers.20.ls2": "pytorch_model-00001-of-00004.bin",
555
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
556
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
557
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
558
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
559
+ "vision_model.encoder.layers.20.norm1.weight": "pytorch_model-00001-of-00004.bin",
560
+ "vision_model.encoder.layers.20.norm2.weight": "pytorch_model-00001-of-00004.bin",
561
+ "vision_model.encoder.layers.21.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
562
+ "vision_model.encoder.layers.21.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
563
+ "vision_model.encoder.layers.21.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
564
+ "vision_model.encoder.layers.21.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
565
+ "vision_model.encoder.layers.21.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
566
+ "vision_model.encoder.layers.21.ls1": "pytorch_model-00001-of-00004.bin",
567
+ "vision_model.encoder.layers.21.ls2": "pytorch_model-00001-of-00004.bin",
568
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
569
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
570
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
571
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
572
+ "vision_model.encoder.layers.21.norm1.weight": "pytorch_model-00001-of-00004.bin",
573
+ "vision_model.encoder.layers.21.norm2.weight": "pytorch_model-00001-of-00004.bin",
574
+ "vision_model.encoder.layers.22.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
575
+ "vision_model.encoder.layers.22.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
576
+ "vision_model.encoder.layers.22.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
577
+ "vision_model.encoder.layers.22.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
578
+ "vision_model.encoder.layers.22.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
579
+ "vision_model.encoder.layers.22.ls1": "pytorch_model-00001-of-00004.bin",
580
+ "vision_model.encoder.layers.22.ls2": "pytorch_model-00001-of-00004.bin",
581
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
582
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
583
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
584
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
585
+ "vision_model.encoder.layers.22.norm1.weight": "pytorch_model-00001-of-00004.bin",
586
+ "vision_model.encoder.layers.22.norm2.weight": "pytorch_model-00001-of-00004.bin",
587
+ "vision_model.encoder.layers.23.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
588
+ "vision_model.encoder.layers.23.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
589
+ "vision_model.encoder.layers.23.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
590
+ "vision_model.encoder.layers.23.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
591
+ "vision_model.encoder.layers.23.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
592
+ "vision_model.encoder.layers.23.ls1": "pytorch_model-00001-of-00004.bin",
593
+ "vision_model.encoder.layers.23.ls2": "pytorch_model-00001-of-00004.bin",
594
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
595
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
596
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
597
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
598
+ "vision_model.encoder.layers.23.norm1.weight": "pytorch_model-00001-of-00004.bin",
599
+ "vision_model.encoder.layers.23.norm2.weight": "pytorch_model-00001-of-00004.bin",
600
+ "vision_model.encoder.layers.24.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
601
+ "vision_model.encoder.layers.24.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
602
+ "vision_model.encoder.layers.24.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
603
+ "vision_model.encoder.layers.24.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
604
+ "vision_model.encoder.layers.24.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
605
+ "vision_model.encoder.layers.24.ls1": "pytorch_model-00001-of-00004.bin",
606
+ "vision_model.encoder.layers.24.ls2": "pytorch_model-00001-of-00004.bin",
607
+ "vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
608
+ "vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
609
+ "vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
610
+ "vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
611
+ "vision_model.encoder.layers.24.norm1.weight": "pytorch_model-00001-of-00004.bin",
612
+ "vision_model.encoder.layers.24.norm2.weight": "pytorch_model-00001-of-00004.bin",
613
+ "vision_model.encoder.layers.25.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
614
+ "vision_model.encoder.layers.25.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
615
+ "vision_model.encoder.layers.25.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
616
+ "vision_model.encoder.layers.25.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
617
+ "vision_model.encoder.layers.25.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
618
+ "vision_model.encoder.layers.25.ls1": "pytorch_model-00001-of-00004.bin",
619
+ "vision_model.encoder.layers.25.ls2": "pytorch_model-00001-of-00004.bin",
620
+ "vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
621
+ "vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
622
+ "vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
623
+ "vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
624
+ "vision_model.encoder.layers.25.norm1.weight": "pytorch_model-00001-of-00004.bin",
625
+ "vision_model.encoder.layers.25.norm2.weight": "pytorch_model-00001-of-00004.bin",
626
+ "vision_model.encoder.layers.26.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
627
+ "vision_model.encoder.layers.26.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
628
+ "vision_model.encoder.layers.26.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
629
+ "vision_model.encoder.layers.26.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
630
+ "vision_model.encoder.layers.26.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
631
+ "vision_model.encoder.layers.26.ls1": "pytorch_model-00001-of-00004.bin",
632
+ "vision_model.encoder.layers.26.ls2": "pytorch_model-00001-of-00004.bin",
633
+ "vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
634
+ "vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
635
+ "vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
636
+ "vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
637
+ "vision_model.encoder.layers.26.norm1.weight": "pytorch_model-00001-of-00004.bin",
638
+ "vision_model.encoder.layers.26.norm2.weight": "pytorch_model-00001-of-00004.bin",
639
+ "vision_model.encoder.layers.27.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
640
+ "vision_model.encoder.layers.27.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
641
+ "vision_model.encoder.layers.27.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
642
+ "vision_model.encoder.layers.27.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
643
+ "vision_model.encoder.layers.27.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
644
+ "vision_model.encoder.layers.27.ls1": "pytorch_model-00001-of-00004.bin",
645
+ "vision_model.encoder.layers.27.ls2": "pytorch_model-00001-of-00004.bin",
646
+ "vision_model.encoder.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
647
+ "vision_model.encoder.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
648
+ "vision_model.encoder.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
649
+ "vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
650
+ "vision_model.encoder.layers.27.norm1.weight": "pytorch_model-00001-of-00004.bin",
651
+ "vision_model.encoder.layers.27.norm2.weight": "pytorch_model-00001-of-00004.bin",
652
+ "vision_model.encoder.layers.28.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
653
+ "vision_model.encoder.layers.28.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
654
+ "vision_model.encoder.layers.28.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
655
+ "vision_model.encoder.layers.28.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
656
+ "vision_model.encoder.layers.28.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
657
+ "vision_model.encoder.layers.28.ls1": "pytorch_model-00001-of-00004.bin",
658
+ "vision_model.encoder.layers.28.ls2": "pytorch_model-00001-of-00004.bin",
659
+ "vision_model.encoder.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
660
+ "vision_model.encoder.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
661
+ "vision_model.encoder.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
662
+ "vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
663
+ "vision_model.encoder.layers.28.norm1.weight": "pytorch_model-00001-of-00004.bin",
664
+ "vision_model.encoder.layers.28.norm2.weight": "pytorch_model-00001-of-00004.bin",
665
+ "vision_model.encoder.layers.29.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
666
+ "vision_model.encoder.layers.29.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
667
+ "vision_model.encoder.layers.29.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
668
+ "vision_model.encoder.layers.29.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
669
+ "vision_model.encoder.layers.29.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
670
+ "vision_model.encoder.layers.29.ls1": "pytorch_model-00001-of-00004.bin",
671
+ "vision_model.encoder.layers.29.ls2": "pytorch_model-00001-of-00004.bin",
672
+ "vision_model.encoder.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
673
+ "vision_model.encoder.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
674
+ "vision_model.encoder.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
675
+ "vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
676
+ "vision_model.encoder.layers.29.norm1.weight": "pytorch_model-00001-of-00004.bin",
677
+ "vision_model.encoder.layers.29.norm2.weight": "pytorch_model-00001-of-00004.bin",
678
+ "vision_model.encoder.layers.3.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
679
+ "vision_model.encoder.layers.3.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
680
+ "vision_model.encoder.layers.3.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
681
+ "vision_model.encoder.layers.3.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
682
+ "vision_model.encoder.layers.3.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
683
+ "vision_model.encoder.layers.3.ls1": "pytorch_model-00001-of-00004.bin",
684
+ "vision_model.encoder.layers.3.ls2": "pytorch_model-00001-of-00004.bin",
685
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
686
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
687
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
688
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
689
+ "vision_model.encoder.layers.3.norm1.weight": "pytorch_model-00001-of-00004.bin",
690
+ "vision_model.encoder.layers.3.norm2.weight": "pytorch_model-00001-of-00004.bin",
691
+ "vision_model.encoder.layers.30.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
692
+ "vision_model.encoder.layers.30.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
693
+ "vision_model.encoder.layers.30.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
694
+ "vision_model.encoder.layers.30.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
695
+ "vision_model.encoder.layers.30.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
696
+ "vision_model.encoder.layers.30.ls1": "pytorch_model-00001-of-00004.bin",
697
+ "vision_model.encoder.layers.30.ls2": "pytorch_model-00001-of-00004.bin",
698
+ "vision_model.encoder.layers.30.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
699
+ "vision_model.encoder.layers.30.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
700
+ "vision_model.encoder.layers.30.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
701
+ "vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
702
+ "vision_model.encoder.layers.30.norm1.weight": "pytorch_model-00001-of-00004.bin",
703
+ "vision_model.encoder.layers.30.norm2.weight": "pytorch_model-00001-of-00004.bin",
704
+ "vision_model.encoder.layers.31.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
705
+ "vision_model.encoder.layers.31.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
706
+ "vision_model.encoder.layers.31.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
707
+ "vision_model.encoder.layers.31.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
708
+ "vision_model.encoder.layers.31.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
709
+ "vision_model.encoder.layers.31.ls1": "pytorch_model-00001-of-00004.bin",
710
+ "vision_model.encoder.layers.31.ls2": "pytorch_model-00001-of-00004.bin",
711
+ "vision_model.encoder.layers.31.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
712
+ "vision_model.encoder.layers.31.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
713
+ "vision_model.encoder.layers.31.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
714
+ "vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
715
+ "vision_model.encoder.layers.31.norm1.weight": "pytorch_model-00001-of-00004.bin",
716
+ "vision_model.encoder.layers.31.norm2.weight": "pytorch_model-00001-of-00004.bin",
717
+ "vision_model.encoder.layers.32.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
718
+ "vision_model.encoder.layers.32.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
719
+ "vision_model.encoder.layers.32.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
720
+ "vision_model.encoder.layers.32.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
721
+ "vision_model.encoder.layers.32.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
722
+ "vision_model.encoder.layers.32.ls1": "pytorch_model-00001-of-00004.bin",
723
+ "vision_model.encoder.layers.32.ls2": "pytorch_model-00001-of-00004.bin",
724
+ "vision_model.encoder.layers.32.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
725
+ "vision_model.encoder.layers.32.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
726
+ "vision_model.encoder.layers.32.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
727
+ "vision_model.encoder.layers.32.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
728
+ "vision_model.encoder.layers.32.norm1.weight": "pytorch_model-00001-of-00004.bin",
729
+ "vision_model.encoder.layers.32.norm2.weight": "pytorch_model-00001-of-00004.bin",
730
+ "vision_model.encoder.layers.33.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
731
+ "vision_model.encoder.layers.33.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
732
+ "vision_model.encoder.layers.33.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
733
+ "vision_model.encoder.layers.33.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
734
+ "vision_model.encoder.layers.33.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
735
+ "vision_model.encoder.layers.33.ls1": "pytorch_model-00001-of-00004.bin",
736
+ "vision_model.encoder.layers.33.ls2": "pytorch_model-00001-of-00004.bin",
737
+ "vision_model.encoder.layers.33.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
738
+ "vision_model.encoder.layers.33.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
739
+ "vision_model.encoder.layers.33.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
740
+ "vision_model.encoder.layers.33.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
741
+ "vision_model.encoder.layers.33.norm1.weight": "pytorch_model-00001-of-00004.bin",
742
+ "vision_model.encoder.layers.33.norm2.weight": "pytorch_model-00001-of-00004.bin",
743
+ "vision_model.encoder.layers.34.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
744
+ "vision_model.encoder.layers.34.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
745
+ "vision_model.encoder.layers.34.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
746
+ "vision_model.encoder.layers.34.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
747
+ "vision_model.encoder.layers.34.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
748
+ "vision_model.encoder.layers.34.ls1": "pytorch_model-00001-of-00004.bin",
749
+ "vision_model.encoder.layers.34.ls2": "pytorch_model-00001-of-00004.bin",
750
+ "vision_model.encoder.layers.34.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
751
+ "vision_model.encoder.layers.34.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
752
+ "vision_model.encoder.layers.34.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
753
+ "vision_model.encoder.layers.34.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
754
+ "vision_model.encoder.layers.34.norm1.weight": "pytorch_model-00001-of-00004.bin",
755
+ "vision_model.encoder.layers.34.norm2.weight": "pytorch_model-00001-of-00004.bin",
756
+ "vision_model.encoder.layers.35.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
757
+ "vision_model.encoder.layers.35.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
758
+ "vision_model.encoder.layers.35.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
759
+ "vision_model.encoder.layers.35.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
760
+ "vision_model.encoder.layers.35.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
761
+ "vision_model.encoder.layers.35.ls1": "pytorch_model-00001-of-00004.bin",
762
+ "vision_model.encoder.layers.35.ls2": "pytorch_model-00001-of-00004.bin",
763
+ "vision_model.encoder.layers.35.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
764
+ "vision_model.encoder.layers.35.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
765
+ "vision_model.encoder.layers.35.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
766
+ "vision_model.encoder.layers.35.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
767
+ "vision_model.encoder.layers.35.norm1.weight": "pytorch_model-00001-of-00004.bin",
768
+ "vision_model.encoder.layers.35.norm2.weight": "pytorch_model-00001-of-00004.bin",
769
+ "vision_model.encoder.layers.36.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
770
+ "vision_model.encoder.layers.36.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
771
+ "vision_model.encoder.layers.36.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
772
+ "vision_model.encoder.layers.36.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
773
+ "vision_model.encoder.layers.36.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
774
+ "vision_model.encoder.layers.36.ls1": "pytorch_model-00001-of-00004.bin",
775
+ "vision_model.encoder.layers.36.ls2": "pytorch_model-00001-of-00004.bin",
776
+ "vision_model.encoder.layers.36.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
777
+ "vision_model.encoder.layers.36.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
778
+ "vision_model.encoder.layers.36.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
779
+ "vision_model.encoder.layers.36.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
780
+ "vision_model.encoder.layers.36.norm1.weight": "pytorch_model-00001-of-00004.bin",
781
+ "vision_model.encoder.layers.36.norm2.weight": "pytorch_model-00001-of-00004.bin",
782
+ "vision_model.encoder.layers.37.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
783
+ "vision_model.encoder.layers.37.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
784
+ "vision_model.encoder.layers.37.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
785
+ "vision_model.encoder.layers.37.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
786
+ "vision_model.encoder.layers.37.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
787
+ "vision_model.encoder.layers.37.ls1": "pytorch_model-00001-of-00004.bin",
788
+ "vision_model.encoder.layers.37.ls2": "pytorch_model-00001-of-00004.bin",
789
+ "vision_model.encoder.layers.37.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
790
+ "vision_model.encoder.layers.37.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
791
+ "vision_model.encoder.layers.37.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
792
+ "vision_model.encoder.layers.37.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
793
+ "vision_model.encoder.layers.37.norm1.weight": "pytorch_model-00001-of-00004.bin",
794
+ "vision_model.encoder.layers.37.norm2.weight": "pytorch_model-00001-of-00004.bin",
795
+ "vision_model.encoder.layers.38.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
796
+ "vision_model.encoder.layers.38.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
797
+ "vision_model.encoder.layers.38.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
798
+ "vision_model.encoder.layers.38.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
799
+ "vision_model.encoder.layers.38.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
800
+ "vision_model.encoder.layers.38.ls1": "pytorch_model-00001-of-00004.bin",
801
+ "vision_model.encoder.layers.38.ls2": "pytorch_model-00001-of-00004.bin",
802
+ "vision_model.encoder.layers.38.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
803
+ "vision_model.encoder.layers.38.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
804
+ "vision_model.encoder.layers.38.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
805
+ "vision_model.encoder.layers.38.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
806
+ "vision_model.encoder.layers.38.norm1.weight": "pytorch_model-00001-of-00004.bin",
807
+ "vision_model.encoder.layers.38.norm2.weight": "pytorch_model-00001-of-00004.bin",
808
+ "vision_model.encoder.layers.39.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
809
+ "vision_model.encoder.layers.39.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
810
+ "vision_model.encoder.layers.39.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
811
+ "vision_model.encoder.layers.39.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
812
+ "vision_model.encoder.layers.39.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
813
+ "vision_model.encoder.layers.39.ls1": "pytorch_model-00001-of-00004.bin",
814
+ "vision_model.encoder.layers.39.ls2": "pytorch_model-00001-of-00004.bin",
815
+ "vision_model.encoder.layers.39.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
816
+ "vision_model.encoder.layers.39.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
817
+ "vision_model.encoder.layers.39.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
818
+ "vision_model.encoder.layers.39.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
819
+ "vision_model.encoder.layers.39.norm1.weight": "pytorch_model-00001-of-00004.bin",
820
+ "vision_model.encoder.layers.39.norm2.weight": "pytorch_model-00001-of-00004.bin",
821
+ "vision_model.encoder.layers.4.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
822
+ "vision_model.encoder.layers.4.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
823
+ "vision_model.encoder.layers.4.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
824
+ "vision_model.encoder.layers.4.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
825
+ "vision_model.encoder.layers.4.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
826
+ "vision_model.encoder.layers.4.ls1": "pytorch_model-00001-of-00004.bin",
827
+ "vision_model.encoder.layers.4.ls2": "pytorch_model-00001-of-00004.bin",
828
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
829
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
830
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
831
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
832
+ "vision_model.encoder.layers.4.norm1.weight": "pytorch_model-00001-of-00004.bin",
833
+ "vision_model.encoder.layers.4.norm2.weight": "pytorch_model-00001-of-00004.bin",
834
+ "vision_model.encoder.layers.40.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
835
+ "vision_model.encoder.layers.40.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
836
+ "vision_model.encoder.layers.40.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
837
+ "vision_model.encoder.layers.40.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
838
+ "vision_model.encoder.layers.40.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
839
+ "vision_model.encoder.layers.40.ls1": "pytorch_model-00001-of-00004.bin",
840
+ "vision_model.encoder.layers.40.ls2": "pytorch_model-00001-of-00004.bin",
841
+ "vision_model.encoder.layers.40.mlp.fc1.bias": "pytorch_model-00002-of-00004.bin",
842
+ "vision_model.encoder.layers.40.mlp.fc1.weight": "pytorch_model-00002-of-00004.bin",
843
+ "vision_model.encoder.layers.40.mlp.fc2.bias": "pytorch_model-00002-of-00004.bin",
844
+ "vision_model.encoder.layers.40.mlp.fc2.weight": "pytorch_model-00002-of-00004.bin",
845
+ "vision_model.encoder.layers.40.norm1.weight": "pytorch_model-00002-of-00004.bin",
846
+ "vision_model.encoder.layers.40.norm2.weight": "pytorch_model-00002-of-00004.bin",
847
+ "vision_model.encoder.layers.41.attn.k_norm.weight": "pytorch_model-00002-of-00004.bin",
848
+ "vision_model.encoder.layers.41.attn.proj.bias": "pytorch_model-00002-of-00004.bin",
849
+ "vision_model.encoder.layers.41.attn.proj.weight": "pytorch_model-00002-of-00004.bin",
850
+ "vision_model.encoder.layers.41.attn.q_norm.weight": "pytorch_model-00002-of-00004.bin",
851
+ "vision_model.encoder.layers.41.attn.qkv.weight": "pytorch_model-00002-of-00004.bin",
852
+ "vision_model.encoder.layers.41.ls1": "pytorch_model-00002-of-00004.bin",
853
+ "vision_model.encoder.layers.41.ls2": "pytorch_model-00002-of-00004.bin",
854
+ "vision_model.encoder.layers.41.mlp.fc1.bias": "pytorch_model-00002-of-00004.bin",
855
+ "vision_model.encoder.layers.41.mlp.fc1.weight": "pytorch_model-00002-of-00004.bin",
856
+ "vision_model.encoder.layers.41.mlp.fc2.bias": "pytorch_model-00002-of-00004.bin",
857
+ "vision_model.encoder.layers.41.mlp.fc2.weight": "pytorch_model-00002-of-00004.bin",
858
+ "vision_model.encoder.layers.41.norm1.weight": "pytorch_model-00002-of-00004.bin",
859
+ "vision_model.encoder.layers.41.norm2.weight": "pytorch_model-00002-of-00004.bin",
860
+ "vision_model.encoder.layers.42.attn.k_norm.weight": "pytorch_model-00002-of-00004.bin",
861
+ "vision_model.encoder.layers.42.attn.proj.bias": "pytorch_model-00002-of-00004.bin",
862
+ "vision_model.encoder.layers.42.attn.proj.weight": "pytorch_model-00002-of-00004.bin",
863
+ "vision_model.encoder.layers.42.attn.q_norm.weight": "pytorch_model-00002-of-00004.bin",
864
+ "vision_model.encoder.layers.42.attn.qkv.weight": "pytorch_model-00002-of-00004.bin",
865
+ "vision_model.encoder.layers.42.ls1": "pytorch_model-00002-of-00004.bin",
866
+ "vision_model.encoder.layers.42.ls2": "pytorch_model-00002-of-00004.bin",
867
+ "vision_model.encoder.layers.42.mlp.fc1.bias": "pytorch_model-00002-of-00004.bin",
868
+ "vision_model.encoder.layers.42.mlp.fc1.weight": "pytorch_model-00002-of-00004.bin",
869
+ "vision_model.encoder.layers.42.mlp.fc2.bias": "pytorch_model-00002-of-00004.bin",
870
+ "vision_model.encoder.layers.42.mlp.fc2.weight": "pytorch_model-00002-of-00004.bin",
871
+ "vision_model.encoder.layers.42.norm1.weight": "pytorch_model-00002-of-00004.bin",
872
+ "vision_model.encoder.layers.42.norm2.weight": "pytorch_model-00002-of-00004.bin",
873
+ "vision_model.encoder.layers.43.attn.k_norm.weight": "pytorch_model-00002-of-00004.bin",
874
+ "vision_model.encoder.layers.43.attn.proj.bias": "pytorch_model-00002-of-00004.bin",
875
+ "vision_model.encoder.layers.43.attn.proj.weight": "pytorch_model-00002-of-00004.bin",
876
+ "vision_model.encoder.layers.43.attn.q_norm.weight": "pytorch_model-00002-of-00004.bin",
877
+ "vision_model.encoder.layers.43.attn.qkv.weight": "pytorch_model-00002-of-00004.bin",
878
+ "vision_model.encoder.layers.43.ls1": "pytorch_model-00002-of-00004.bin",
879
+ "vision_model.encoder.layers.43.ls2": "pytorch_model-00002-of-00004.bin",
880
+ "vision_model.encoder.layers.43.mlp.fc1.bias": "pytorch_model-00002-of-00004.bin",
881
+ "vision_model.encoder.layers.43.mlp.fc1.weight": "pytorch_model-00002-of-00004.bin",
882
+ "vision_model.encoder.layers.43.mlp.fc2.bias": "pytorch_model-00002-of-00004.bin",
883
+ "vision_model.encoder.layers.43.mlp.fc2.weight": "pytorch_model-00002-of-00004.bin",
884
+ "vision_model.encoder.layers.43.norm1.weight": "pytorch_model-00002-of-00004.bin",
885
+ "vision_model.encoder.layers.43.norm2.weight": "pytorch_model-00002-of-00004.bin",
886
+ "vision_model.encoder.layers.44.attn.k_norm.weight": "pytorch_model-00002-of-00004.bin",
887
+ "vision_model.encoder.layers.44.attn.proj.bias": "pytorch_model-00002-of-00004.bin",
888
+ "vision_model.encoder.layers.44.attn.proj.weight": "pytorch_model-00002-of-00004.bin",
889
+ "vision_model.encoder.layers.44.attn.q_norm.weight": "pytorch_model-00002-of-00004.bin",
890
+ "vision_model.encoder.layers.44.attn.qkv.weight": "pytorch_model-00002-of-00004.bin",
891
+ "vision_model.encoder.layers.44.ls1": "pytorch_model-00002-of-00004.bin",
892
+ "vision_model.encoder.layers.44.ls2": "pytorch_model-00002-of-00004.bin",
893
+ "vision_model.encoder.layers.44.mlp.fc1.bias": "pytorch_model-00002-of-00004.bin",
894
+ "vision_model.encoder.layers.44.mlp.fc1.weight": "pytorch_model-00002-of-00004.bin",
895
+ "vision_model.encoder.layers.44.mlp.fc2.bias": "pytorch_model-00002-of-00004.bin",
896
+ "vision_model.encoder.layers.44.mlp.fc2.weight": "pytorch_model-00002-of-00004.bin",
897
+ "vision_model.encoder.layers.44.norm1.weight": "pytorch_model-00002-of-00004.bin",
898
+ "vision_model.encoder.layers.44.norm2.weight": "pytorch_model-00002-of-00004.bin",
899
+ "vision_model.encoder.layers.45.attn.k_norm.weight": "pytorch_model-00002-of-00004.bin",
900
+ "vision_model.encoder.layers.45.attn.proj.bias": "pytorch_model-00002-of-00004.bin",
901
+ "vision_model.encoder.layers.45.attn.proj.weight": "pytorch_model-00002-of-00004.bin",
902
+ "vision_model.encoder.layers.45.attn.q_norm.weight": "pytorch_model-00002-of-00004.bin",
903
+ "vision_model.encoder.layers.45.attn.qkv.weight": "pytorch_model-00002-of-00004.bin",
904
+ "vision_model.encoder.layers.45.ls1": "pytorch_model-00002-of-00004.bin",
905
+ "vision_model.encoder.layers.45.ls2": "pytorch_model-00002-of-00004.bin",
906
+ "vision_model.encoder.layers.45.mlp.fc1.bias": "pytorch_model-00002-of-00004.bin",
907
+ "vision_model.encoder.layers.45.mlp.fc1.weight": "pytorch_model-00002-of-00004.bin",
908
+ "vision_model.encoder.layers.45.mlp.fc2.bias": "pytorch_model-00002-of-00004.bin",
909
+ "vision_model.encoder.layers.45.mlp.fc2.weight": "pytorch_model-00002-of-00004.bin",
910
+ "vision_model.encoder.layers.45.norm1.weight": "pytorch_model-00002-of-00004.bin",
911
+ "vision_model.encoder.layers.45.norm2.weight": "pytorch_model-00002-of-00004.bin",
912
+ "vision_model.encoder.layers.46.attn.k_norm.weight": "pytorch_model-00002-of-00004.bin",
913
+ "vision_model.encoder.layers.46.attn.proj.bias": "pytorch_model-00002-of-00004.bin",
914
+ "vision_model.encoder.layers.46.attn.proj.weight": "pytorch_model-00002-of-00004.bin",
915
+ "vision_model.encoder.layers.46.attn.q_norm.weight": "pytorch_model-00002-of-00004.bin",
916
+ "vision_model.encoder.layers.46.attn.qkv.weight": "pytorch_model-00002-of-00004.bin",
917
+ "vision_model.encoder.layers.46.ls1": "pytorch_model-00002-of-00004.bin",
918
+ "vision_model.encoder.layers.46.ls2": "pytorch_model-00002-of-00004.bin",
919
+ "vision_model.encoder.layers.46.mlp.fc1.bias": "pytorch_model-00002-of-00004.bin",
920
+ "vision_model.encoder.layers.46.mlp.fc1.weight": "pytorch_model-00002-of-00004.bin",
921
+ "vision_model.encoder.layers.46.mlp.fc2.bias": "pytorch_model-00002-of-00004.bin",
922
+ "vision_model.encoder.layers.46.mlp.fc2.weight": "pytorch_model-00002-of-00004.bin",
923
+ "vision_model.encoder.layers.46.norm1.weight": "pytorch_model-00002-of-00004.bin",
924
+ "vision_model.encoder.layers.46.norm2.weight": "pytorch_model-00002-of-00004.bin",
925
+ "vision_model.encoder.layers.47.attn.k_norm.weight": "pytorch_model-00002-of-00004.bin",
926
+ "vision_model.encoder.layers.47.attn.proj.bias": "pytorch_model-00002-of-00004.bin",
927
+ "vision_model.encoder.layers.47.attn.proj.weight": "pytorch_model-00002-of-00004.bin",
928
+ "vision_model.encoder.layers.47.attn.q_norm.weight": "pytorch_model-00002-of-00004.bin",
929
+ "vision_model.encoder.layers.47.attn.qkv.weight": "pytorch_model-00002-of-00004.bin",
930
+ "vision_model.encoder.layers.47.ls1": "pytorch_model-00002-of-00004.bin",
931
+ "vision_model.encoder.layers.47.ls2": "pytorch_model-00002-of-00004.bin",
932
+ "vision_model.encoder.layers.47.mlp.fc1.bias": "pytorch_model-00002-of-00004.bin",
933
+ "vision_model.encoder.layers.47.mlp.fc1.weight": "pytorch_model-00002-of-00004.bin",
934
+ "vision_model.encoder.layers.47.mlp.fc2.bias": "pytorch_model-00002-of-00004.bin",
935
+ "vision_model.encoder.layers.47.mlp.fc2.weight": "pytorch_model-00002-of-00004.bin",
936
+ "vision_model.encoder.layers.47.norm1.weight": "pytorch_model-00002-of-00004.bin",
937
+ "vision_model.encoder.layers.47.norm2.weight": "pytorch_model-00002-of-00004.bin",
938
+ "vision_model.encoder.layers.5.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
939
+ "vision_model.encoder.layers.5.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
940
+ "vision_model.encoder.layers.5.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
941
+ "vision_model.encoder.layers.5.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
942
+ "vision_model.encoder.layers.5.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
943
+ "vision_model.encoder.layers.5.ls1": "pytorch_model-00001-of-00004.bin",
944
+ "vision_model.encoder.layers.5.ls2": "pytorch_model-00001-of-00004.bin",
945
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
946
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
947
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
948
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
949
+ "vision_model.encoder.layers.5.norm1.weight": "pytorch_model-00001-of-00004.bin",
950
+ "vision_model.encoder.layers.5.norm2.weight": "pytorch_model-00001-of-00004.bin",
951
+ "vision_model.encoder.layers.6.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
952
+ "vision_model.encoder.layers.6.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
953
+ "vision_model.encoder.layers.6.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
954
+ "vision_model.encoder.layers.6.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
955
+ "vision_model.encoder.layers.6.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
956
+ "vision_model.encoder.layers.6.ls1": "pytorch_model-00001-of-00004.bin",
957
+ "vision_model.encoder.layers.6.ls2": "pytorch_model-00001-of-00004.bin",
958
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
959
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
960
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
961
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
962
+ "vision_model.encoder.layers.6.norm1.weight": "pytorch_model-00001-of-00004.bin",
963
+ "vision_model.encoder.layers.6.norm2.weight": "pytorch_model-00001-of-00004.bin",
964
+ "vision_model.encoder.layers.7.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
965
+ "vision_model.encoder.layers.7.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
966
+ "vision_model.encoder.layers.7.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
967
+ "vision_model.encoder.layers.7.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
968
+ "vision_model.encoder.layers.7.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
969
+ "vision_model.encoder.layers.7.ls1": "pytorch_model-00001-of-00004.bin",
970
+ "vision_model.encoder.layers.7.ls2": "pytorch_model-00001-of-00004.bin",
971
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
972
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
973
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
974
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
975
+ "vision_model.encoder.layers.7.norm1.weight": "pytorch_model-00001-of-00004.bin",
976
+ "vision_model.encoder.layers.7.norm2.weight": "pytorch_model-00001-of-00004.bin",
977
+ "vision_model.encoder.layers.8.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
978
+ "vision_model.encoder.layers.8.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
979
+ "vision_model.encoder.layers.8.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
980
+ "vision_model.encoder.layers.8.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
981
+ "vision_model.encoder.layers.8.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
982
+ "vision_model.encoder.layers.8.ls1": "pytorch_model-00001-of-00004.bin",
983
+ "vision_model.encoder.layers.8.ls2": "pytorch_model-00001-of-00004.bin",
984
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
985
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
986
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
987
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
988
+ "vision_model.encoder.layers.8.norm1.weight": "pytorch_model-00001-of-00004.bin",
989
+ "vision_model.encoder.layers.8.norm2.weight": "pytorch_model-00001-of-00004.bin",
990
+ "vision_model.encoder.layers.9.attn.k_norm.weight": "pytorch_model-00001-of-00004.bin",
991
+ "vision_model.encoder.layers.9.attn.proj.bias": "pytorch_model-00001-of-00004.bin",
992
+ "vision_model.encoder.layers.9.attn.proj.weight": "pytorch_model-00001-of-00004.bin",
993
+ "vision_model.encoder.layers.9.attn.q_norm.weight": "pytorch_model-00001-of-00004.bin",
994
+ "vision_model.encoder.layers.9.attn.qkv.weight": "pytorch_model-00001-of-00004.bin",
995
+ "vision_model.encoder.layers.9.ls1": "pytorch_model-00001-of-00004.bin",
996
+ "vision_model.encoder.layers.9.ls2": "pytorch_model-00001-of-00004.bin",
997
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00004.bin",
998
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00004.bin",
999
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00004.bin",
1000
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00004.bin",
1001
+ "vision_model.encoder.layers.9.norm1.weight": "pytorch_model-00001-of-00004.bin",
1002
+ "vision_model.encoder.layers.9.norm2.weight": "pytorch_model-00001-of-00004.bin"
1003
+ }
1004
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<human>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<bot>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<img>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</img>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<vid>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "</vid>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<box>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "</box>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<ref>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "</ref>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ }
73
+ ],
74
+ "bos_token": {
75
+ "content": "<s>",
76
+ "lstrip": false,
77
+ "normalized": false,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ },
81
+ "eos_token": {
82
+ "content": "</s>",
83
+ "lstrip": false,
84
+ "normalized": false,
85
+ "rstrip": false,
86
+ "single_word": false
87
+ },
88
+ "pad_token": "<unk>",
89
+ "unk_token": {
90
+ "content": "<unk>",
91
+ "lstrip": false,
92
+ "normalized": false,
93
+ "rstrip": false,
94
+ "single_word": false
95
+ }
96
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bf0f5a9395cc99ed08d134e1a0ead7ff7d554e76665ec22387b90da2b644253
3
+ size 619167
tokenizer_config.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "41906": {
30
+ "content": "<human>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "41907": {
38
+ "content": "<bot>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "41908": {
46
+ "content": "<img>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "41909": {
54
+ "content": "</img>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "41910": {
62
+ "content": "<vid>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "41911": {
70
+ "content": "</vid>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "41912": {
78
+ "content": "<box>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "41913": {
86
+ "content": "</box>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "41914": {
94
+ "content": "<ref>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "41915": {
102
+ "content": "</ref>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ }
109
+ },
110
+ "additional_special_tokens": [
111
+ "<human>",
112
+ "<bot>",
113
+ "<img>",
114
+ "</img>",
115
+ "<vid>",
116
+ "</vid>",
117
+ "<box>",
118
+ "</box>",
119
+ "<ref>",
120
+ "</ref>"
121
+ ],
122
+ "bos_token": {
123
+ "__type": "AddedToken",
124
+ "content": "<s>",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false
129
+ },
130
+ "clean_up_tokenization_spaces": false,
131
+ "eos_token": {
132
+ "__type": "AddedToken",
133
+ "content": "</s>",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false
138
+ },
139
+ "legacy": true,
140
+ "model_max_length": 768,
141
+ "pad_token": {
142
+ "__type": "AddedToken",
143
+ "content": "<unk>",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false
148
+ },
149
+ "padding_side": "right",
150
+ "sp_model_kwargs": {},
151
+ "spaces_between_special_tokens": false,
152
+ "tokenizer_class": "LlamaTokenizer",
153
+ "unk_token": {
154
+ "__type": "AddedToken",
155
+ "content": "<unk>",
156
+ "lstrip": false,
157
+ "normalized": true,
158
+ "rstrip": false,
159
+ "single_word": false
160
+ },
161
+ "use_default_system_prompt": true,
162
+ "use_fast": true
163
+ }