tanahhh commited on
Commit
11b5adc
1 Parent(s): 5b9ad83

Upload VideoBlipForConditionalGeneration

Browse files
config.json ADDED
@@ -0,0 +1,259 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "6e723d92ee91ebcee4ba74d7017632f11ff4217b",
3
+ "_name_or_path": "Salesforce/blip2-opt-2.7b",
4
+ "architectures": [
5
+ "VideoBlipForConditionalGeneration"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "initializer_range": 0.02,
9
+ "llm_hidden_size": 4096,
10
+ "model_type": "video_blip",
11
+ "num_frames": 1,
12
+ "num_query_tokens": 32,
13
+ "qformer_config": {
14
+ "_name_or_path": "",
15
+ "add_cross_attention": false,
16
+ "architectures": null,
17
+ "attention_probs_dropout_prob": 0.1,
18
+ "bad_words_ids": null,
19
+ "begin_suppress_tokens": null,
20
+ "bos_token_id": null,
21
+ "chunk_size_feed_forward": 0,
22
+ "classifier_dropout": null,
23
+ "cross_attention_frequency": 2,
24
+ "cross_attention_hidden_size": null,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "early_stopping": false,
29
+ "encoder_hidden_size": 1408,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": null,
32
+ "exponential_decay_length_penalty": null,
33
+ "finetuning_task": null,
34
+ "forced_bos_token_id": null,
35
+ "forced_eos_token_id": null,
36
+ "hidden_act": "gelu",
37
+ "hidden_dropout_prob": 0.1,
38
+ "hidden_size": 768,
39
+ "id2label": {
40
+ "0": "LABEL_0",
41
+ "1": "LABEL_1"
42
+ },
43
+ "initializer_range": 0.02,
44
+ "intermediate_size": 3072,
45
+ "is_decoder": false,
46
+ "is_encoder_decoder": false,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "layer_norm_eps": 1e-12,
52
+ "length_penalty": 1.0,
53
+ "max_length": 20,
54
+ "max_position_embeddings": 512,
55
+ "min_length": 0,
56
+ "model_type": "blip_2_qformer",
57
+ "no_repeat_ngram_size": 0,
58
+ "num_attention_heads": 12,
59
+ "num_beam_groups": 1,
60
+ "num_beams": 1,
61
+ "num_hidden_layers": 12,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": 0,
67
+ "position_embedding_type": "absolute",
68
+ "prefix": null,
69
+ "problem_type": null,
70
+ "pruned_heads": {},
71
+ "remove_invalid_values": false,
72
+ "repetition_penalty": 1.0,
73
+ "return_dict": true,
74
+ "return_dict_in_generate": false,
75
+ "sep_token_id": null,
76
+ "suppress_tokens": null,
77
+ "task_specific_params": null,
78
+ "temperature": 1.0,
79
+ "tf_legacy_loss": false,
80
+ "tie_encoder_decoder": false,
81
+ "tie_word_embeddings": true,
82
+ "tokenizer_class": null,
83
+ "top_k": 50,
84
+ "top_p": 1.0,
85
+ "torch_dtype": null,
86
+ "torchscript": false,
87
+ "transformers_version": "4.34.1",
88
+ "typical_p": 1.0,
89
+ "use_bfloat16": false,
90
+ "vocab_size": 30522
91
+ },
92
+ "text_config": {
93
+ "_name_or_path": "stabilityai/japanese-stablelm-base-alpha-7b",
94
+ "add_cross_attention": false,
95
+ "architectures": [
96
+ "JapaneseStableLMAlphaForCausalLM"
97
+ ],
98
+ "auto_map": {
99
+ "AutoConfig": "stabilityai/japanese-stablelm-base-alpha-7b--configuration_japanese_stablelm_alpha.JapaneseStableLMAlphaConfig",
100
+ "AutoModelForCausalLM": "stabilityai/japanese-stablelm-base-alpha-7b--modeling_japanese_stablelm_alpha.JapaneseStableLMAlphaForCausalLM"
101
+ },
102
+ "bad_words_ids": null,
103
+ "begin_suppress_tokens": null,
104
+ "bos_token_id": 3,
105
+ "chunk_size_feed_forward": 0,
106
+ "classifier_dropout": 0.1,
107
+ "cross_attention_hidden_size": null,
108
+ "decoder_start_token_id": null,
109
+ "diversity_penalty": 0.0,
110
+ "do_sample": false,
111
+ "early_stopping": false,
112
+ "encoder_no_repeat_ngram_size": 0,
113
+ "eos_token_id": 3,
114
+ "exponential_decay_length_penalty": null,
115
+ "finetuning_task": null,
116
+ "forced_bos_token_id": null,
117
+ "forced_eos_token_id": null,
118
+ "hidden_act": "silu",
119
+ "hidden_size": 4096,
120
+ "id2label": {
121
+ "0": "LABEL_0",
122
+ "1": "LABEL_1"
123
+ },
124
+ "initializer_range": 0.02,
125
+ "is_decoder": false,
126
+ "is_encoder_decoder": false,
127
+ "label2id": {
128
+ "LABEL_0": 0,
129
+ "LABEL_1": 1
130
+ },
131
+ "layer_norm_eps": 1e-05,
132
+ "length_penalty": 1.0,
133
+ "max_length": 20,
134
+ "max_position_embeddings": 2048,
135
+ "min_length": 0,
136
+ "model_type": "",
137
+ "no_repeat_ngram_size": 0,
138
+ "num_attention_heads": 32,
139
+ "num_beam_groups": 1,
140
+ "num_beams": 1,
141
+ "num_hidden_layers": 32,
142
+ "num_return_sequences": 1,
143
+ "output_attentions": false,
144
+ "output_hidden_states": false,
145
+ "output_scores": false,
146
+ "pad_token_id": null,
147
+ "prefix": null,
148
+ "problem_type": null,
149
+ "pruned_heads": {},
150
+ "remove_invalid_values": false,
151
+ "repetition_penalty": 1.0,
152
+ "return_dict": true,
153
+ "return_dict_in_generate": false,
154
+ "rotary_emb_base": 10000,
155
+ "rotary_pct": 0.25,
156
+ "rotary_scale_base": 512,
157
+ "sep_token_id": null,
158
+ "suppress_tokens": null,
159
+ "task_specific_params": null,
160
+ "temperature": 1.0,
161
+ "tf_legacy_loss": false,
162
+ "tie_encoder_decoder": false,
163
+ "tie_word_embeddings": false,
164
+ "tokenizer_class": null,
165
+ "top_k": 50,
166
+ "top_p": 1.0,
167
+ "torch_dtype": "float16",
168
+ "torchscript": false,
169
+ "transformers_version": "4.34.1",
170
+ "typical_p": 1.0,
171
+ "use_bfloat16": false,
172
+ "use_bias_in_mlp": false,
173
+ "use_cache": true,
174
+ "use_parallel_residual": true,
175
+ "vocab_size": 65536
176
+ },
177
+ "torch_dtype": "float16",
178
+ "transformers_version": null,
179
+ "use_decoder_only_language_model": true,
180
+ "vision_config": {
181
+ "_name_or_path": "",
182
+ "add_cross_attention": false,
183
+ "architectures": null,
184
+ "attention_dropout": 0.0,
185
+ "bad_words_ids": null,
186
+ "begin_suppress_tokens": null,
187
+ "bos_token_id": null,
188
+ "chunk_size_feed_forward": 0,
189
+ "cross_attention_hidden_size": null,
190
+ "decoder_start_token_id": null,
191
+ "diversity_penalty": 0.0,
192
+ "do_sample": false,
193
+ "dropout": 0.0,
194
+ "early_stopping": false,
195
+ "encoder_no_repeat_ngram_size": 0,
196
+ "eos_token_id": null,
197
+ "exponential_decay_length_penalty": null,
198
+ "finetuning_task": null,
199
+ "forced_bos_token_id": null,
200
+ "forced_eos_token_id": null,
201
+ "hidden_act": "gelu",
202
+ "hidden_size": 1408,
203
+ "id2label": {
204
+ "0": "LABEL_0",
205
+ "1": "LABEL_1"
206
+ },
207
+ "image_size": 224,
208
+ "initializer_factor": 1.0,
209
+ "initializer_range": 1e-10,
210
+ "intermediate_size": 6144,
211
+ "is_decoder": false,
212
+ "is_encoder_decoder": false,
213
+ "label2id": {
214
+ "LABEL_0": 0,
215
+ "LABEL_1": 1
216
+ },
217
+ "layer_norm_eps": 1e-06,
218
+ "length_penalty": 1.0,
219
+ "max_length": 20,
220
+ "min_length": 0,
221
+ "model_type": "blip_2_vision_model",
222
+ "no_repeat_ngram_size": 0,
223
+ "num_attention_heads": 16,
224
+ "num_beam_groups": 1,
225
+ "num_beams": 1,
226
+ "num_channels": 3,
227
+ "num_hidden_layers": 39,
228
+ "num_return_sequences": 1,
229
+ "output_attentions": false,
230
+ "output_hidden_states": false,
231
+ "output_scores": false,
232
+ "pad_token_id": null,
233
+ "patch_size": 14,
234
+ "prefix": null,
235
+ "problem_type": null,
236
+ "projection_dim": 512,
237
+ "pruned_heads": {},
238
+ "qkv_bias": true,
239
+ "remove_invalid_values": false,
240
+ "repetition_penalty": 1.0,
241
+ "return_dict": true,
242
+ "return_dict_in_generate": false,
243
+ "sep_token_id": null,
244
+ "suppress_tokens": null,
245
+ "task_specific_params": null,
246
+ "temperature": 1.0,
247
+ "tf_legacy_loss": false,
248
+ "tie_encoder_decoder": false,
249
+ "tie_word_embeddings": true,
250
+ "tokenizer_class": null,
251
+ "top_k": 50,
252
+ "top_p": 1.0,
253
+ "torch_dtype": null,
254
+ "torchscript": false,
255
+ "transformers_version": "4.34.1",
256
+ "typical_p": 1.0,
257
+ "use_bfloat16": false
258
+ }
259
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.34.1"
7
+ }
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed877c60e28122ef9f631f4402234b9641699907dcfc87c80e8542db9c702ad6
3
+ size 9883661814
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:041f36c3c71a5c0e1cd5095ff1156f9dbb70bcb792338a386cba04027ca5d999
3
+ size 6474205103
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,1013 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16357512058
4
+ },
5
+ "weight_map": {
6
+ "img_temperal_embedding.0": "pytorch_model-00002-of-00002.bin",
7
+ "itm_head.bias": "pytorch_model-00002-of-00002.bin",
8
+ "itm_head.weight": "pytorch_model-00002-of-00002.bin",
9
+ "language_model.embed_out.weight": "pytorch_model-00002-of-00002.bin",
10
+ "language_model.transformer.embed_in.weight": "pytorch_model-00001-of-00002.bin",
11
+ "language_model.transformer.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
12
+ "language_model.transformer.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
13
+ "language_model.transformer.layers.0.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
14
+ "language_model.transformer.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
15
+ "language_model.transformer.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
16
+ "language_model.transformer.layers.0.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
17
+ "language_model.transformer.layers.0.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
18
+ "language_model.transformer.layers.0.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
19
+ "language_model.transformer.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
20
+ "language_model.transformer.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
21
+ "language_model.transformer.layers.1.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
22
+ "language_model.transformer.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
23
+ "language_model.transformer.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
24
+ "language_model.transformer.layers.1.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
25
+ "language_model.transformer.layers.1.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
26
+ "language_model.transformer.layers.1.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
27
+ "language_model.transformer.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
28
+ "language_model.transformer.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
29
+ "language_model.transformer.layers.10.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
30
+ "language_model.transformer.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
31
+ "language_model.transformer.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
32
+ "language_model.transformer.layers.10.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
33
+ "language_model.transformer.layers.10.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
34
+ "language_model.transformer.layers.10.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
35
+ "language_model.transformer.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
36
+ "language_model.transformer.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
37
+ "language_model.transformer.layers.11.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
38
+ "language_model.transformer.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
39
+ "language_model.transformer.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
40
+ "language_model.transformer.layers.11.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
41
+ "language_model.transformer.layers.11.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
42
+ "language_model.transformer.layers.11.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
43
+ "language_model.transformer.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
44
+ "language_model.transformer.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
45
+ "language_model.transformer.layers.12.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
46
+ "language_model.transformer.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
47
+ "language_model.transformer.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
48
+ "language_model.transformer.layers.12.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
49
+ "language_model.transformer.layers.12.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
50
+ "language_model.transformer.layers.12.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
51
+ "language_model.transformer.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
52
+ "language_model.transformer.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
53
+ "language_model.transformer.layers.13.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
54
+ "language_model.transformer.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
55
+ "language_model.transformer.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
56
+ "language_model.transformer.layers.13.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
57
+ "language_model.transformer.layers.13.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
58
+ "language_model.transformer.layers.13.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
59
+ "language_model.transformer.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
60
+ "language_model.transformer.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
61
+ "language_model.transformer.layers.14.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
62
+ "language_model.transformer.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
63
+ "language_model.transformer.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
64
+ "language_model.transformer.layers.14.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
65
+ "language_model.transformer.layers.14.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
66
+ "language_model.transformer.layers.14.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
67
+ "language_model.transformer.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
68
+ "language_model.transformer.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "language_model.transformer.layers.15.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
70
+ "language_model.transformer.layers.15.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
71
+ "language_model.transformer.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
72
+ "language_model.transformer.layers.15.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
73
+ "language_model.transformer.layers.15.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
74
+ "language_model.transformer.layers.15.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
75
+ "language_model.transformer.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
76
+ "language_model.transformer.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
77
+ "language_model.transformer.layers.16.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
78
+ "language_model.transformer.layers.16.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
79
+ "language_model.transformer.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
80
+ "language_model.transformer.layers.16.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
81
+ "language_model.transformer.layers.16.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
82
+ "language_model.transformer.layers.16.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
83
+ "language_model.transformer.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
84
+ "language_model.transformer.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
85
+ "language_model.transformer.layers.17.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
86
+ "language_model.transformer.layers.17.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
87
+ "language_model.transformer.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
88
+ "language_model.transformer.layers.17.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
89
+ "language_model.transformer.layers.17.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
90
+ "language_model.transformer.layers.17.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
91
+ "language_model.transformer.layers.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
92
+ "language_model.transformer.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
93
+ "language_model.transformer.layers.18.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
94
+ "language_model.transformer.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
95
+ "language_model.transformer.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
96
+ "language_model.transformer.layers.18.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
97
+ "language_model.transformer.layers.18.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
98
+ "language_model.transformer.layers.18.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
99
+ "language_model.transformer.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
100
+ "language_model.transformer.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
101
+ "language_model.transformer.layers.19.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
102
+ "language_model.transformer.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
103
+ "language_model.transformer.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
104
+ "language_model.transformer.layers.19.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
105
+ "language_model.transformer.layers.19.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
106
+ "language_model.transformer.layers.19.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
107
+ "language_model.transformer.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
108
+ "language_model.transformer.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
109
+ "language_model.transformer.layers.2.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
110
+ "language_model.transformer.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
111
+ "language_model.transformer.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
112
+ "language_model.transformer.layers.2.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
113
+ "language_model.transformer.layers.2.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
114
+ "language_model.transformer.layers.2.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
115
+ "language_model.transformer.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
116
+ "language_model.transformer.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
117
+ "language_model.transformer.layers.20.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
118
+ "language_model.transformer.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
119
+ "language_model.transformer.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
120
+ "language_model.transformer.layers.20.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
121
+ "language_model.transformer.layers.20.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
122
+ "language_model.transformer.layers.20.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
123
+ "language_model.transformer.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
124
+ "language_model.transformer.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
125
+ "language_model.transformer.layers.21.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
126
+ "language_model.transformer.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
127
+ "language_model.transformer.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
128
+ "language_model.transformer.layers.21.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
129
+ "language_model.transformer.layers.21.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
130
+ "language_model.transformer.layers.21.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
131
+ "language_model.transformer.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
132
+ "language_model.transformer.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
133
+ "language_model.transformer.layers.22.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
134
+ "language_model.transformer.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
135
+ "language_model.transformer.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
136
+ "language_model.transformer.layers.22.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
137
+ "language_model.transformer.layers.22.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
138
+ "language_model.transformer.layers.22.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
139
+ "language_model.transformer.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
140
+ "language_model.transformer.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
141
+ "language_model.transformer.layers.23.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
142
+ "language_model.transformer.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
143
+ "language_model.transformer.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
144
+ "language_model.transformer.layers.23.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
145
+ "language_model.transformer.layers.23.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
146
+ "language_model.transformer.layers.23.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
147
+ "language_model.transformer.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
148
+ "language_model.transformer.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
149
+ "language_model.transformer.layers.24.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
150
+ "language_model.transformer.layers.24.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
151
+ "language_model.transformer.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
152
+ "language_model.transformer.layers.24.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
153
+ "language_model.transformer.layers.24.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
154
+ "language_model.transformer.layers.24.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
155
+ "language_model.transformer.layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
156
+ "language_model.transformer.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
157
+ "language_model.transformer.layers.25.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
158
+ "language_model.transformer.layers.25.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
159
+ "language_model.transformer.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
160
+ "language_model.transformer.layers.25.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
161
+ "language_model.transformer.layers.25.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
162
+ "language_model.transformer.layers.25.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
163
+ "language_model.transformer.layers.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
164
+ "language_model.transformer.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
165
+ "language_model.transformer.layers.26.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
166
+ "language_model.transformer.layers.26.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
167
+ "language_model.transformer.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
168
+ "language_model.transformer.layers.26.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
169
+ "language_model.transformer.layers.26.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
170
+ "language_model.transformer.layers.26.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
171
+ "language_model.transformer.layers.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
172
+ "language_model.transformer.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
173
+ "language_model.transformer.layers.27.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
174
+ "language_model.transformer.layers.27.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
175
+ "language_model.transformer.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
176
+ "language_model.transformer.layers.27.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
177
+ "language_model.transformer.layers.27.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
178
+ "language_model.transformer.layers.27.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
179
+ "language_model.transformer.layers.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
180
+ "language_model.transformer.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
181
+ "language_model.transformer.layers.28.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
182
+ "language_model.transformer.layers.28.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
183
+ "language_model.transformer.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
184
+ "language_model.transformer.layers.28.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
185
+ "language_model.transformer.layers.28.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
186
+ "language_model.transformer.layers.28.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
187
+ "language_model.transformer.layers.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
188
+ "language_model.transformer.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "language_model.transformer.layers.29.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
190
+ "language_model.transformer.layers.29.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
191
+ "language_model.transformer.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
192
+ "language_model.transformer.layers.29.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
193
+ "language_model.transformer.layers.29.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
194
+ "language_model.transformer.layers.29.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
195
+ "language_model.transformer.layers.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
196
+ "language_model.transformer.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
197
+ "language_model.transformer.layers.3.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
198
+ "language_model.transformer.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
199
+ "language_model.transformer.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
200
+ "language_model.transformer.layers.3.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
201
+ "language_model.transformer.layers.3.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
202
+ "language_model.transformer.layers.3.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
203
+ "language_model.transformer.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
204
+ "language_model.transformer.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
205
+ "language_model.transformer.layers.30.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
206
+ "language_model.transformer.layers.30.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
207
+ "language_model.transformer.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
208
+ "language_model.transformer.layers.30.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
209
+ "language_model.transformer.layers.30.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
210
+ "language_model.transformer.layers.30.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
211
+ "language_model.transformer.layers.30.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
212
+ "language_model.transformer.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
213
+ "language_model.transformer.layers.31.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
214
+ "language_model.transformer.layers.31.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
215
+ "language_model.transformer.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
216
+ "language_model.transformer.layers.31.attention.rotary_emb.scale": "pytorch_model-00002-of-00002.bin",
217
+ "language_model.transformer.layers.31.mlp.out_proj.weight": "pytorch_model-00002-of-00002.bin",
218
+ "language_model.transformer.layers.31.mlp.packed_input_proj.weight": "pytorch_model-00002-of-00002.bin",
219
+ "language_model.transformer.layers.31.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
220
+ "language_model.transformer.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
221
+ "language_model.transformer.layers.4.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
222
+ "language_model.transformer.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
223
+ "language_model.transformer.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
224
+ "language_model.transformer.layers.4.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
225
+ "language_model.transformer.layers.4.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
226
+ "language_model.transformer.layers.4.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
227
+ "language_model.transformer.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
228
+ "language_model.transformer.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
229
+ "language_model.transformer.layers.5.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
230
+ "language_model.transformer.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
231
+ "language_model.transformer.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
232
+ "language_model.transformer.layers.5.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
233
+ "language_model.transformer.layers.5.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
234
+ "language_model.transformer.layers.5.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
235
+ "language_model.transformer.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
236
+ "language_model.transformer.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
237
+ "language_model.transformer.layers.6.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
238
+ "language_model.transformer.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
239
+ "language_model.transformer.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
240
+ "language_model.transformer.layers.6.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
241
+ "language_model.transformer.layers.6.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
242
+ "language_model.transformer.layers.6.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
243
+ "language_model.transformer.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
244
+ "language_model.transformer.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
245
+ "language_model.transformer.layers.7.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
246
+ "language_model.transformer.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
247
+ "language_model.transformer.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
248
+ "language_model.transformer.layers.7.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
249
+ "language_model.transformer.layers.7.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
250
+ "language_model.transformer.layers.7.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
251
+ "language_model.transformer.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
252
+ "language_model.transformer.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
253
+ "language_model.transformer.layers.8.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
254
+ "language_model.transformer.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
255
+ "language_model.transformer.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
256
+ "language_model.transformer.layers.8.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
257
+ "language_model.transformer.layers.8.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
258
+ "language_model.transformer.layers.8.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
259
+ "language_model.transformer.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
260
+ "language_model.transformer.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
261
+ "language_model.transformer.layers.9.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
262
+ "language_model.transformer.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
263
+ "language_model.transformer.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
264
+ "language_model.transformer.layers.9.attention.rotary_emb.scale": "pytorch_model-00001-of-00002.bin",
265
+ "language_model.transformer.layers.9.mlp.out_proj.weight": "pytorch_model-00001-of-00002.bin",
266
+ "language_model.transformer.layers.9.mlp.packed_input_proj.weight": "pytorch_model-00001-of-00002.bin",
267
+ "language_model.transformer.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
268
+ "language_model.transformer.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
269
+ "language_projection.bias": "pytorch_model-00001-of-00002.bin",
270
+ "language_projection.weight": "pytorch_model-00001-of-00002.bin",
271
+ "qformer.cls.predictions.bias": "pytorch_model-00001-of-00002.bin",
272
+ "qformer.cls.predictions.decoder.bias": "pytorch_model-00001-of-00002.bin",
273
+ "qformer.cls.predictions.decoder.weight": "pytorch_model-00001-of-00002.bin",
274
+ "qformer.cls.predictions.transform.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
275
+ "qformer.cls.predictions.transform.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
276
+ "qformer.cls.predictions.transform.dense.bias": "pytorch_model-00001-of-00002.bin",
277
+ "qformer.cls.predictions.transform.dense.weight": "pytorch_model-00001-of-00002.bin",
278
+ "qformer.embeddings.layernorm.bias": "pytorch_model-00001-of-00002.bin",
279
+ "qformer.embeddings.layernorm.weight": "pytorch_model-00001-of-00002.bin",
280
+ "qformer.embeddings.position_embeddings.weight": "pytorch_model-00001-of-00002.bin",
281
+ "qformer.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
282
+ "qformer.encoder.layer.0.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
283
+ "qformer.encoder.layer.0.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
284
+ "qformer.encoder.layer.0.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
285
+ "qformer.encoder.layer.0.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
286
+ "qformer.encoder.layer.0.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
287
+ "qformer.encoder.layer.0.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
288
+ "qformer.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
289
+ "qformer.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
290
+ "qformer.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
291
+ "qformer.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
292
+ "qformer.encoder.layer.0.crossattention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
293
+ "qformer.encoder.layer.0.crossattention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
294
+ "qformer.encoder.layer.0.crossattention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
295
+ "qformer.encoder.layer.0.crossattention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
296
+ "qformer.encoder.layer.0.crossattention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
297
+ "qformer.encoder.layer.0.crossattention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
298
+ "qformer.encoder.layer.0.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
299
+ "qformer.encoder.layer.0.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
300
+ "qformer.encoder.layer.0.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
301
+ "qformer.encoder.layer.0.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
302
+ "qformer.encoder.layer.0.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
303
+ "qformer.encoder.layer.0.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
304
+ "qformer.encoder.layer.0.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
305
+ "qformer.encoder.layer.0.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
306
+ "qformer.encoder.layer.0.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
307
+ "qformer.encoder.layer.0.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
308
+ "qformer.encoder.layer.1.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
309
+ "qformer.encoder.layer.1.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
310
+ "qformer.encoder.layer.1.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
311
+ "qformer.encoder.layer.1.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
312
+ "qformer.encoder.layer.1.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
313
+ "qformer.encoder.layer.1.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
314
+ "qformer.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
315
+ "qformer.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
316
+ "qformer.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
317
+ "qformer.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
318
+ "qformer.encoder.layer.1.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
319
+ "qformer.encoder.layer.1.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
320
+ "qformer.encoder.layer.1.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
321
+ "qformer.encoder.layer.1.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
322
+ "qformer.encoder.layer.1.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
323
+ "qformer.encoder.layer.1.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
324
+ "qformer.encoder.layer.10.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
325
+ "qformer.encoder.layer.10.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
326
+ "qformer.encoder.layer.10.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
327
+ "qformer.encoder.layer.10.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
328
+ "qformer.encoder.layer.10.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
329
+ "qformer.encoder.layer.10.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
330
+ "qformer.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
331
+ "qformer.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
332
+ "qformer.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
333
+ "qformer.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
334
+ "qformer.encoder.layer.10.crossattention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
335
+ "qformer.encoder.layer.10.crossattention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
336
+ "qformer.encoder.layer.10.crossattention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
337
+ "qformer.encoder.layer.10.crossattention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
338
+ "qformer.encoder.layer.10.crossattention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
339
+ "qformer.encoder.layer.10.crossattention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
340
+ "qformer.encoder.layer.10.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
341
+ "qformer.encoder.layer.10.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
342
+ "qformer.encoder.layer.10.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
343
+ "qformer.encoder.layer.10.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
344
+ "qformer.encoder.layer.10.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
345
+ "qformer.encoder.layer.10.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
346
+ "qformer.encoder.layer.10.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
347
+ "qformer.encoder.layer.10.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
348
+ "qformer.encoder.layer.10.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
349
+ "qformer.encoder.layer.10.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
350
+ "qformer.encoder.layer.11.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
351
+ "qformer.encoder.layer.11.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
352
+ "qformer.encoder.layer.11.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
353
+ "qformer.encoder.layer.11.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
354
+ "qformer.encoder.layer.11.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
355
+ "qformer.encoder.layer.11.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
356
+ "qformer.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
357
+ "qformer.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
358
+ "qformer.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
359
+ "qformer.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
360
+ "qformer.encoder.layer.11.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
361
+ "qformer.encoder.layer.11.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
362
+ "qformer.encoder.layer.11.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
363
+ "qformer.encoder.layer.11.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
364
+ "qformer.encoder.layer.11.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
365
+ "qformer.encoder.layer.11.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
366
+ "qformer.encoder.layer.2.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
367
+ "qformer.encoder.layer.2.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
368
+ "qformer.encoder.layer.2.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
369
+ "qformer.encoder.layer.2.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
370
+ "qformer.encoder.layer.2.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
371
+ "qformer.encoder.layer.2.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
372
+ "qformer.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
373
+ "qformer.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
374
+ "qformer.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
375
+ "qformer.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
376
+ "qformer.encoder.layer.2.crossattention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
377
+ "qformer.encoder.layer.2.crossattention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
378
+ "qformer.encoder.layer.2.crossattention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
379
+ "qformer.encoder.layer.2.crossattention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
380
+ "qformer.encoder.layer.2.crossattention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
381
+ "qformer.encoder.layer.2.crossattention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
382
+ "qformer.encoder.layer.2.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
383
+ "qformer.encoder.layer.2.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
384
+ "qformer.encoder.layer.2.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
385
+ "qformer.encoder.layer.2.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
386
+ "qformer.encoder.layer.2.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
387
+ "qformer.encoder.layer.2.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
388
+ "qformer.encoder.layer.2.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
389
+ "qformer.encoder.layer.2.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
390
+ "qformer.encoder.layer.2.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
391
+ "qformer.encoder.layer.2.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
392
+ "qformer.encoder.layer.3.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
393
+ "qformer.encoder.layer.3.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
394
+ "qformer.encoder.layer.3.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
395
+ "qformer.encoder.layer.3.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
396
+ "qformer.encoder.layer.3.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
397
+ "qformer.encoder.layer.3.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
398
+ "qformer.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
399
+ "qformer.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
400
+ "qformer.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
401
+ "qformer.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
402
+ "qformer.encoder.layer.3.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
403
+ "qformer.encoder.layer.3.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
404
+ "qformer.encoder.layer.3.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
405
+ "qformer.encoder.layer.3.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
406
+ "qformer.encoder.layer.3.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
407
+ "qformer.encoder.layer.3.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
408
+ "qformer.encoder.layer.4.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
409
+ "qformer.encoder.layer.4.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
410
+ "qformer.encoder.layer.4.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
411
+ "qformer.encoder.layer.4.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
412
+ "qformer.encoder.layer.4.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
413
+ "qformer.encoder.layer.4.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
414
+ "qformer.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
415
+ "qformer.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
416
+ "qformer.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
417
+ "qformer.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
418
+ "qformer.encoder.layer.4.crossattention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
419
+ "qformer.encoder.layer.4.crossattention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
420
+ "qformer.encoder.layer.4.crossattention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
421
+ "qformer.encoder.layer.4.crossattention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
422
+ "qformer.encoder.layer.4.crossattention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
423
+ "qformer.encoder.layer.4.crossattention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
424
+ "qformer.encoder.layer.4.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
425
+ "qformer.encoder.layer.4.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
426
+ "qformer.encoder.layer.4.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
427
+ "qformer.encoder.layer.4.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
428
+ "qformer.encoder.layer.4.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
429
+ "qformer.encoder.layer.4.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
430
+ "qformer.encoder.layer.4.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
431
+ "qformer.encoder.layer.4.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
432
+ "qformer.encoder.layer.4.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
433
+ "qformer.encoder.layer.4.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
434
+ "qformer.encoder.layer.5.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
435
+ "qformer.encoder.layer.5.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
436
+ "qformer.encoder.layer.5.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
437
+ "qformer.encoder.layer.5.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
438
+ "qformer.encoder.layer.5.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
439
+ "qformer.encoder.layer.5.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
440
+ "qformer.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
441
+ "qformer.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
442
+ "qformer.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
443
+ "qformer.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
444
+ "qformer.encoder.layer.5.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
445
+ "qformer.encoder.layer.5.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
446
+ "qformer.encoder.layer.5.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
447
+ "qformer.encoder.layer.5.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
448
+ "qformer.encoder.layer.5.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
449
+ "qformer.encoder.layer.5.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
450
+ "qformer.encoder.layer.6.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
451
+ "qformer.encoder.layer.6.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
452
+ "qformer.encoder.layer.6.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
453
+ "qformer.encoder.layer.6.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
454
+ "qformer.encoder.layer.6.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
455
+ "qformer.encoder.layer.6.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
456
+ "qformer.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
457
+ "qformer.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
458
+ "qformer.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
459
+ "qformer.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
460
+ "qformer.encoder.layer.6.crossattention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
461
+ "qformer.encoder.layer.6.crossattention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
462
+ "qformer.encoder.layer.6.crossattention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
463
+ "qformer.encoder.layer.6.crossattention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
464
+ "qformer.encoder.layer.6.crossattention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
465
+ "qformer.encoder.layer.6.crossattention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
466
+ "qformer.encoder.layer.6.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
467
+ "qformer.encoder.layer.6.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
468
+ "qformer.encoder.layer.6.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
469
+ "qformer.encoder.layer.6.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
470
+ "qformer.encoder.layer.6.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
471
+ "qformer.encoder.layer.6.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
472
+ "qformer.encoder.layer.6.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
473
+ "qformer.encoder.layer.6.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
474
+ "qformer.encoder.layer.6.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
475
+ "qformer.encoder.layer.6.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
476
+ "qformer.encoder.layer.7.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
477
+ "qformer.encoder.layer.7.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
478
+ "qformer.encoder.layer.7.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
479
+ "qformer.encoder.layer.7.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
480
+ "qformer.encoder.layer.7.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
481
+ "qformer.encoder.layer.7.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
482
+ "qformer.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
483
+ "qformer.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
484
+ "qformer.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
485
+ "qformer.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
486
+ "qformer.encoder.layer.7.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
487
+ "qformer.encoder.layer.7.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
488
+ "qformer.encoder.layer.7.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
489
+ "qformer.encoder.layer.7.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
490
+ "qformer.encoder.layer.7.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
491
+ "qformer.encoder.layer.7.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
492
+ "qformer.encoder.layer.8.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
493
+ "qformer.encoder.layer.8.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
494
+ "qformer.encoder.layer.8.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
495
+ "qformer.encoder.layer.8.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
496
+ "qformer.encoder.layer.8.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
497
+ "qformer.encoder.layer.8.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
498
+ "qformer.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
499
+ "qformer.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
500
+ "qformer.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
501
+ "qformer.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
502
+ "qformer.encoder.layer.8.crossattention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
503
+ "qformer.encoder.layer.8.crossattention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
504
+ "qformer.encoder.layer.8.crossattention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
505
+ "qformer.encoder.layer.8.crossattention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
506
+ "qformer.encoder.layer.8.crossattention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
507
+ "qformer.encoder.layer.8.crossattention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
508
+ "qformer.encoder.layer.8.crossattention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
509
+ "qformer.encoder.layer.8.crossattention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
510
+ "qformer.encoder.layer.8.crossattention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
511
+ "qformer.encoder.layer.8.crossattention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
512
+ "qformer.encoder.layer.8.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
513
+ "qformer.encoder.layer.8.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
514
+ "qformer.encoder.layer.8.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
515
+ "qformer.encoder.layer.8.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
516
+ "qformer.encoder.layer.8.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
517
+ "qformer.encoder.layer.8.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
518
+ "qformer.encoder.layer.9.attention.attention.key.bias": "pytorch_model-00001-of-00002.bin",
519
+ "qformer.encoder.layer.9.attention.attention.key.weight": "pytorch_model-00001-of-00002.bin",
520
+ "qformer.encoder.layer.9.attention.attention.query.bias": "pytorch_model-00001-of-00002.bin",
521
+ "qformer.encoder.layer.9.attention.attention.query.weight": "pytorch_model-00001-of-00002.bin",
522
+ "qformer.encoder.layer.9.attention.attention.value.bias": "pytorch_model-00001-of-00002.bin",
523
+ "qformer.encoder.layer.9.attention.attention.value.weight": "pytorch_model-00001-of-00002.bin",
524
+ "qformer.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
525
+ "qformer.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
526
+ "qformer.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00001-of-00002.bin",
527
+ "qformer.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00001-of-00002.bin",
528
+ "qformer.encoder.layer.9.intermediate_query.dense.bias": "pytorch_model-00001-of-00002.bin",
529
+ "qformer.encoder.layer.9.intermediate_query.dense.weight": "pytorch_model-00001-of-00002.bin",
530
+ "qformer.encoder.layer.9.output_query.LayerNorm.bias": "pytorch_model-00001-of-00002.bin",
531
+ "qformer.encoder.layer.9.output_query.LayerNorm.weight": "pytorch_model-00001-of-00002.bin",
532
+ "qformer.encoder.layer.9.output_query.dense.bias": "pytorch_model-00001-of-00002.bin",
533
+ "qformer.encoder.layer.9.output_query.dense.weight": "pytorch_model-00001-of-00002.bin",
534
+ "qformer.layernorm.bias": "pytorch_model-00001-of-00002.bin",
535
+ "qformer.layernorm.weight": "pytorch_model-00001-of-00002.bin",
536
+ "query_tokens": "pytorch_model-00001-of-00002.bin",
537
+ "temp": "pytorch_model-00001-of-00002.bin",
538
+ "vision_model.embeddings.class_embedding": "pytorch_model-00001-of-00002.bin",
539
+ "vision_model.embeddings.patch_embedding.bias": "pytorch_model-00001-of-00002.bin",
540
+ "vision_model.embeddings.patch_embedding.weight": "pytorch_model-00001-of-00002.bin",
541
+ "vision_model.embeddings.position_embedding": "pytorch_model-00001-of-00002.bin",
542
+ "vision_model.encoder.layers.0.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
543
+ "vision_model.encoder.layers.0.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
544
+ "vision_model.encoder.layers.0.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
545
+ "vision_model.encoder.layers.0.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
546
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
547
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
548
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
549
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
550
+ "vision_model.encoder.layers.0.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
551
+ "vision_model.encoder.layers.0.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
552
+ "vision_model.encoder.layers.0.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
553
+ "vision_model.encoder.layers.0.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
554
+ "vision_model.encoder.layers.1.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
555
+ "vision_model.encoder.layers.1.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
556
+ "vision_model.encoder.layers.1.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
557
+ "vision_model.encoder.layers.1.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
558
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
559
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
560
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
561
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
562
+ "vision_model.encoder.layers.1.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
563
+ "vision_model.encoder.layers.1.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
564
+ "vision_model.encoder.layers.1.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
565
+ "vision_model.encoder.layers.1.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
566
+ "vision_model.encoder.layers.10.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
567
+ "vision_model.encoder.layers.10.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
568
+ "vision_model.encoder.layers.10.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
569
+ "vision_model.encoder.layers.10.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
570
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
571
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
572
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
573
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
574
+ "vision_model.encoder.layers.10.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
575
+ "vision_model.encoder.layers.10.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
576
+ "vision_model.encoder.layers.10.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
577
+ "vision_model.encoder.layers.10.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
578
+ "vision_model.encoder.layers.11.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
579
+ "vision_model.encoder.layers.11.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
580
+ "vision_model.encoder.layers.11.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
581
+ "vision_model.encoder.layers.11.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
582
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
583
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
584
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
585
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
586
+ "vision_model.encoder.layers.11.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
587
+ "vision_model.encoder.layers.11.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
588
+ "vision_model.encoder.layers.11.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
589
+ "vision_model.encoder.layers.11.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
590
+ "vision_model.encoder.layers.12.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
591
+ "vision_model.encoder.layers.12.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
592
+ "vision_model.encoder.layers.12.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
593
+ "vision_model.encoder.layers.12.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
594
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
595
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
596
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
597
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
598
+ "vision_model.encoder.layers.12.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
599
+ "vision_model.encoder.layers.12.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
600
+ "vision_model.encoder.layers.12.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
601
+ "vision_model.encoder.layers.12.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
602
+ "vision_model.encoder.layers.13.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
603
+ "vision_model.encoder.layers.13.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
604
+ "vision_model.encoder.layers.13.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
605
+ "vision_model.encoder.layers.13.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
606
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
607
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
608
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
609
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
610
+ "vision_model.encoder.layers.13.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
611
+ "vision_model.encoder.layers.13.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
612
+ "vision_model.encoder.layers.13.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
613
+ "vision_model.encoder.layers.13.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
614
+ "vision_model.encoder.layers.14.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
615
+ "vision_model.encoder.layers.14.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
616
+ "vision_model.encoder.layers.14.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
617
+ "vision_model.encoder.layers.14.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
618
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
619
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
620
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
621
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
622
+ "vision_model.encoder.layers.14.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
623
+ "vision_model.encoder.layers.14.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
624
+ "vision_model.encoder.layers.14.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
625
+ "vision_model.encoder.layers.14.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
626
+ "vision_model.encoder.layers.15.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
627
+ "vision_model.encoder.layers.15.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
628
+ "vision_model.encoder.layers.15.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
629
+ "vision_model.encoder.layers.15.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
630
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
631
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
632
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
633
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
634
+ "vision_model.encoder.layers.15.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
635
+ "vision_model.encoder.layers.15.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
636
+ "vision_model.encoder.layers.15.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
637
+ "vision_model.encoder.layers.15.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
638
+ "vision_model.encoder.layers.16.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
639
+ "vision_model.encoder.layers.16.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
640
+ "vision_model.encoder.layers.16.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
641
+ "vision_model.encoder.layers.16.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
642
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
643
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
644
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
645
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
646
+ "vision_model.encoder.layers.16.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
647
+ "vision_model.encoder.layers.16.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
648
+ "vision_model.encoder.layers.16.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
649
+ "vision_model.encoder.layers.16.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
650
+ "vision_model.encoder.layers.17.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
651
+ "vision_model.encoder.layers.17.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
652
+ "vision_model.encoder.layers.17.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
653
+ "vision_model.encoder.layers.17.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
654
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
655
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
656
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
657
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
658
+ "vision_model.encoder.layers.17.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
659
+ "vision_model.encoder.layers.17.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
660
+ "vision_model.encoder.layers.17.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
661
+ "vision_model.encoder.layers.17.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
662
+ "vision_model.encoder.layers.18.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
663
+ "vision_model.encoder.layers.18.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
664
+ "vision_model.encoder.layers.18.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
665
+ "vision_model.encoder.layers.18.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
666
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
667
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
668
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
669
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
670
+ "vision_model.encoder.layers.18.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
671
+ "vision_model.encoder.layers.18.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
672
+ "vision_model.encoder.layers.18.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
673
+ "vision_model.encoder.layers.18.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
674
+ "vision_model.encoder.layers.19.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
675
+ "vision_model.encoder.layers.19.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
676
+ "vision_model.encoder.layers.19.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
677
+ "vision_model.encoder.layers.19.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
678
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
679
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
680
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
681
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
682
+ "vision_model.encoder.layers.19.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
683
+ "vision_model.encoder.layers.19.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
684
+ "vision_model.encoder.layers.19.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
685
+ "vision_model.encoder.layers.19.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
686
+ "vision_model.encoder.layers.2.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
687
+ "vision_model.encoder.layers.2.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
688
+ "vision_model.encoder.layers.2.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
689
+ "vision_model.encoder.layers.2.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
690
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
691
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
692
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
693
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
694
+ "vision_model.encoder.layers.2.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
695
+ "vision_model.encoder.layers.2.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
696
+ "vision_model.encoder.layers.2.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
697
+ "vision_model.encoder.layers.2.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
698
+ "vision_model.encoder.layers.20.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
699
+ "vision_model.encoder.layers.20.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
700
+ "vision_model.encoder.layers.20.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
701
+ "vision_model.encoder.layers.20.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
702
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
703
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
704
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
705
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
706
+ "vision_model.encoder.layers.20.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
707
+ "vision_model.encoder.layers.20.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
708
+ "vision_model.encoder.layers.20.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
709
+ "vision_model.encoder.layers.20.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
710
+ "vision_model.encoder.layers.21.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
711
+ "vision_model.encoder.layers.21.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
712
+ "vision_model.encoder.layers.21.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
713
+ "vision_model.encoder.layers.21.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
714
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
715
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
716
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
717
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
718
+ "vision_model.encoder.layers.21.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
719
+ "vision_model.encoder.layers.21.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
720
+ "vision_model.encoder.layers.21.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
721
+ "vision_model.encoder.layers.21.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
722
+ "vision_model.encoder.layers.22.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
723
+ "vision_model.encoder.layers.22.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
724
+ "vision_model.encoder.layers.22.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
725
+ "vision_model.encoder.layers.22.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
726
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
727
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
728
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
729
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
730
+ "vision_model.encoder.layers.22.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
731
+ "vision_model.encoder.layers.22.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
732
+ "vision_model.encoder.layers.22.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
733
+ "vision_model.encoder.layers.22.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
734
+ "vision_model.encoder.layers.23.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
735
+ "vision_model.encoder.layers.23.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
736
+ "vision_model.encoder.layers.23.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
737
+ "vision_model.encoder.layers.23.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
738
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
739
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
740
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
741
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
742
+ "vision_model.encoder.layers.23.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
743
+ "vision_model.encoder.layers.23.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
744
+ "vision_model.encoder.layers.23.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
745
+ "vision_model.encoder.layers.23.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
746
+ "vision_model.encoder.layers.24.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
747
+ "vision_model.encoder.layers.24.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
748
+ "vision_model.encoder.layers.24.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
749
+ "vision_model.encoder.layers.24.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
750
+ "vision_model.encoder.layers.24.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
751
+ "vision_model.encoder.layers.24.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
752
+ "vision_model.encoder.layers.24.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
753
+ "vision_model.encoder.layers.24.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
754
+ "vision_model.encoder.layers.24.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
755
+ "vision_model.encoder.layers.24.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
756
+ "vision_model.encoder.layers.24.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
757
+ "vision_model.encoder.layers.24.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
758
+ "vision_model.encoder.layers.25.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
759
+ "vision_model.encoder.layers.25.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
760
+ "vision_model.encoder.layers.25.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
761
+ "vision_model.encoder.layers.25.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
762
+ "vision_model.encoder.layers.25.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
763
+ "vision_model.encoder.layers.25.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
764
+ "vision_model.encoder.layers.25.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
765
+ "vision_model.encoder.layers.25.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
766
+ "vision_model.encoder.layers.25.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
767
+ "vision_model.encoder.layers.25.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
768
+ "vision_model.encoder.layers.25.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
769
+ "vision_model.encoder.layers.25.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
770
+ "vision_model.encoder.layers.26.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
771
+ "vision_model.encoder.layers.26.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
772
+ "vision_model.encoder.layers.26.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
773
+ "vision_model.encoder.layers.26.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
774
+ "vision_model.encoder.layers.26.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
775
+ "vision_model.encoder.layers.26.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
776
+ "vision_model.encoder.layers.26.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
777
+ "vision_model.encoder.layers.26.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
778
+ "vision_model.encoder.layers.26.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
779
+ "vision_model.encoder.layers.26.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
780
+ "vision_model.encoder.layers.26.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
781
+ "vision_model.encoder.layers.26.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
782
+ "vision_model.encoder.layers.27.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
783
+ "vision_model.encoder.layers.27.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
784
+ "vision_model.encoder.layers.27.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
785
+ "vision_model.encoder.layers.27.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
786
+ "vision_model.encoder.layers.27.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
787
+ "vision_model.encoder.layers.27.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
788
+ "vision_model.encoder.layers.27.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
789
+ "vision_model.encoder.layers.27.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
790
+ "vision_model.encoder.layers.27.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
791
+ "vision_model.encoder.layers.27.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
792
+ "vision_model.encoder.layers.27.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
793
+ "vision_model.encoder.layers.27.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
794
+ "vision_model.encoder.layers.28.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
795
+ "vision_model.encoder.layers.28.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
796
+ "vision_model.encoder.layers.28.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
797
+ "vision_model.encoder.layers.28.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
798
+ "vision_model.encoder.layers.28.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
799
+ "vision_model.encoder.layers.28.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
800
+ "vision_model.encoder.layers.28.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
801
+ "vision_model.encoder.layers.28.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
802
+ "vision_model.encoder.layers.28.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
803
+ "vision_model.encoder.layers.28.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
804
+ "vision_model.encoder.layers.28.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
805
+ "vision_model.encoder.layers.28.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
806
+ "vision_model.encoder.layers.29.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
807
+ "vision_model.encoder.layers.29.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
808
+ "vision_model.encoder.layers.29.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
809
+ "vision_model.encoder.layers.29.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
810
+ "vision_model.encoder.layers.29.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
811
+ "vision_model.encoder.layers.29.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
812
+ "vision_model.encoder.layers.29.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
813
+ "vision_model.encoder.layers.29.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
814
+ "vision_model.encoder.layers.29.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
815
+ "vision_model.encoder.layers.29.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
816
+ "vision_model.encoder.layers.29.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
817
+ "vision_model.encoder.layers.29.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
818
+ "vision_model.encoder.layers.3.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
819
+ "vision_model.encoder.layers.3.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
820
+ "vision_model.encoder.layers.3.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
821
+ "vision_model.encoder.layers.3.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
822
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
823
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
824
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
825
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
826
+ "vision_model.encoder.layers.3.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
827
+ "vision_model.encoder.layers.3.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
828
+ "vision_model.encoder.layers.3.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
829
+ "vision_model.encoder.layers.3.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
830
+ "vision_model.encoder.layers.30.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
831
+ "vision_model.encoder.layers.30.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
832
+ "vision_model.encoder.layers.30.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
833
+ "vision_model.encoder.layers.30.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
834
+ "vision_model.encoder.layers.30.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
835
+ "vision_model.encoder.layers.30.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
836
+ "vision_model.encoder.layers.30.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
837
+ "vision_model.encoder.layers.30.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
838
+ "vision_model.encoder.layers.30.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
839
+ "vision_model.encoder.layers.30.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
840
+ "vision_model.encoder.layers.30.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
841
+ "vision_model.encoder.layers.30.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
842
+ "vision_model.encoder.layers.31.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
843
+ "vision_model.encoder.layers.31.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
844
+ "vision_model.encoder.layers.31.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
845
+ "vision_model.encoder.layers.31.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
846
+ "vision_model.encoder.layers.31.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
847
+ "vision_model.encoder.layers.31.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
848
+ "vision_model.encoder.layers.31.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
849
+ "vision_model.encoder.layers.31.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
850
+ "vision_model.encoder.layers.31.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
851
+ "vision_model.encoder.layers.31.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
852
+ "vision_model.encoder.layers.31.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
853
+ "vision_model.encoder.layers.31.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
854
+ "vision_model.encoder.layers.32.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
855
+ "vision_model.encoder.layers.32.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
856
+ "vision_model.encoder.layers.32.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
857
+ "vision_model.encoder.layers.32.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
858
+ "vision_model.encoder.layers.32.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
859
+ "vision_model.encoder.layers.32.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
860
+ "vision_model.encoder.layers.32.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
861
+ "vision_model.encoder.layers.32.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
862
+ "vision_model.encoder.layers.32.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
863
+ "vision_model.encoder.layers.32.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
864
+ "vision_model.encoder.layers.32.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
865
+ "vision_model.encoder.layers.32.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
866
+ "vision_model.encoder.layers.33.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
867
+ "vision_model.encoder.layers.33.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
868
+ "vision_model.encoder.layers.33.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
869
+ "vision_model.encoder.layers.33.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
870
+ "vision_model.encoder.layers.33.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
871
+ "vision_model.encoder.layers.33.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
872
+ "vision_model.encoder.layers.33.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
873
+ "vision_model.encoder.layers.33.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
874
+ "vision_model.encoder.layers.33.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
875
+ "vision_model.encoder.layers.33.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
876
+ "vision_model.encoder.layers.33.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
877
+ "vision_model.encoder.layers.33.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
878
+ "vision_model.encoder.layers.34.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
879
+ "vision_model.encoder.layers.34.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
880
+ "vision_model.encoder.layers.34.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
881
+ "vision_model.encoder.layers.34.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
882
+ "vision_model.encoder.layers.34.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
883
+ "vision_model.encoder.layers.34.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
884
+ "vision_model.encoder.layers.34.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
885
+ "vision_model.encoder.layers.34.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
886
+ "vision_model.encoder.layers.34.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
887
+ "vision_model.encoder.layers.34.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
888
+ "vision_model.encoder.layers.34.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
889
+ "vision_model.encoder.layers.34.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
890
+ "vision_model.encoder.layers.35.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
891
+ "vision_model.encoder.layers.35.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
892
+ "vision_model.encoder.layers.35.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
893
+ "vision_model.encoder.layers.35.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
894
+ "vision_model.encoder.layers.35.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
895
+ "vision_model.encoder.layers.35.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
896
+ "vision_model.encoder.layers.35.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
897
+ "vision_model.encoder.layers.35.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
898
+ "vision_model.encoder.layers.35.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
899
+ "vision_model.encoder.layers.35.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
900
+ "vision_model.encoder.layers.35.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
901
+ "vision_model.encoder.layers.35.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
902
+ "vision_model.encoder.layers.36.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
903
+ "vision_model.encoder.layers.36.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
904
+ "vision_model.encoder.layers.36.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
905
+ "vision_model.encoder.layers.36.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
906
+ "vision_model.encoder.layers.36.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
907
+ "vision_model.encoder.layers.36.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
908
+ "vision_model.encoder.layers.36.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
909
+ "vision_model.encoder.layers.36.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
910
+ "vision_model.encoder.layers.36.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
911
+ "vision_model.encoder.layers.36.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
912
+ "vision_model.encoder.layers.36.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
913
+ "vision_model.encoder.layers.36.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
914
+ "vision_model.encoder.layers.37.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
915
+ "vision_model.encoder.layers.37.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
916
+ "vision_model.encoder.layers.37.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
917
+ "vision_model.encoder.layers.37.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
918
+ "vision_model.encoder.layers.37.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
919
+ "vision_model.encoder.layers.37.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
920
+ "vision_model.encoder.layers.37.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
921
+ "vision_model.encoder.layers.37.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
922
+ "vision_model.encoder.layers.37.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
923
+ "vision_model.encoder.layers.37.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
924
+ "vision_model.encoder.layers.37.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
925
+ "vision_model.encoder.layers.37.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
926
+ "vision_model.encoder.layers.38.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
927
+ "vision_model.encoder.layers.38.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
928
+ "vision_model.encoder.layers.38.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
929
+ "vision_model.encoder.layers.38.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
930
+ "vision_model.encoder.layers.38.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
931
+ "vision_model.encoder.layers.38.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
932
+ "vision_model.encoder.layers.38.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
933
+ "vision_model.encoder.layers.38.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
934
+ "vision_model.encoder.layers.38.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
935
+ "vision_model.encoder.layers.38.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
936
+ "vision_model.encoder.layers.38.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
937
+ "vision_model.encoder.layers.38.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
938
+ "vision_model.encoder.layers.4.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
939
+ "vision_model.encoder.layers.4.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
940
+ "vision_model.encoder.layers.4.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
941
+ "vision_model.encoder.layers.4.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
942
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
943
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
944
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
945
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
946
+ "vision_model.encoder.layers.4.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
947
+ "vision_model.encoder.layers.4.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
948
+ "vision_model.encoder.layers.4.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
949
+ "vision_model.encoder.layers.4.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
950
+ "vision_model.encoder.layers.5.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
951
+ "vision_model.encoder.layers.5.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
952
+ "vision_model.encoder.layers.5.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
953
+ "vision_model.encoder.layers.5.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
954
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
955
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
956
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
957
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
958
+ "vision_model.encoder.layers.5.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
959
+ "vision_model.encoder.layers.5.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
960
+ "vision_model.encoder.layers.5.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
961
+ "vision_model.encoder.layers.5.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
962
+ "vision_model.encoder.layers.6.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
963
+ "vision_model.encoder.layers.6.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
964
+ "vision_model.encoder.layers.6.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
965
+ "vision_model.encoder.layers.6.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
966
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
967
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
968
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
969
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
970
+ "vision_model.encoder.layers.6.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
971
+ "vision_model.encoder.layers.6.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
972
+ "vision_model.encoder.layers.6.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
973
+ "vision_model.encoder.layers.6.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
974
+ "vision_model.encoder.layers.7.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
975
+ "vision_model.encoder.layers.7.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
976
+ "vision_model.encoder.layers.7.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
977
+ "vision_model.encoder.layers.7.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
978
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
979
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
980
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
981
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
982
+ "vision_model.encoder.layers.7.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
983
+ "vision_model.encoder.layers.7.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
984
+ "vision_model.encoder.layers.7.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
985
+ "vision_model.encoder.layers.7.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
986
+ "vision_model.encoder.layers.8.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
987
+ "vision_model.encoder.layers.8.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
988
+ "vision_model.encoder.layers.8.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
989
+ "vision_model.encoder.layers.8.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
990
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
991
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
992
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
993
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
994
+ "vision_model.encoder.layers.8.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
995
+ "vision_model.encoder.layers.8.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
996
+ "vision_model.encoder.layers.8.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
997
+ "vision_model.encoder.layers.8.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
998
+ "vision_model.encoder.layers.9.layer_norm1.bias": "pytorch_model-00001-of-00002.bin",
999
+ "vision_model.encoder.layers.9.layer_norm1.weight": "pytorch_model-00001-of-00002.bin",
1000
+ "vision_model.encoder.layers.9.layer_norm2.bias": "pytorch_model-00001-of-00002.bin",
1001
+ "vision_model.encoder.layers.9.layer_norm2.weight": "pytorch_model-00001-of-00002.bin",
1002
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "pytorch_model-00001-of-00002.bin",
1003
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "pytorch_model-00001-of-00002.bin",
1004
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "pytorch_model-00001-of-00002.bin",
1005
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "pytorch_model-00001-of-00002.bin",
1006
+ "vision_model.encoder.layers.9.self_attn.projection.bias": "pytorch_model-00001-of-00002.bin",
1007
+ "vision_model.encoder.layers.9.self_attn.projection.weight": "pytorch_model-00001-of-00002.bin",
1008
+ "vision_model.encoder.layers.9.self_attn.qkv.bias": "pytorch_model-00001-of-00002.bin",
1009
+ "vision_model.encoder.layers.9.self_attn.qkv.weight": "pytorch_model-00001-of-00002.bin",
1010
+ "vision_model.post_layernorm.bias": "pytorch_model-00001-of-00002.bin",
1011
+ "vision_model.post_layernorm.weight": "pytorch_model-00001-of-00002.bin"
1012
+ }
1013
+ }