Hugging Face's logo

rynmurdock
/
Inter-estingVLM

Safetensors
Model card Files
xet
Community
rynmurdock commited on
Commit
20e20bb
·
verified ·
1 Parent(s): 5e57c29

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +300 -0
  2. generation_config.json +9 -0
  3. model-00001-of-00002.safetensors +3 -0
  4. model-00002-of-00002.safetensors +3 -0
  5. model.safetensors.index.json +548 -0
config.json ADDED
@@ -0,0 +1,300 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "inter-est_quite_good",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "OpenGVLab/InternVL2-4B--configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "OpenGVLab/InternVL2-4B--modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "OpenGVLab/InternVL2-4B--modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": true,
14
+ "force_image_size": 448,
15
+ "llm_config": {
16
+ "_name_or_path": "microsoft/Phi-3-mini-128k-instruct",
17
+ "add_cross_attention": false,
18
+ "architectures": [
19
+ "Phi3ForCausalLM"
20
+ ],
21
+ "attention_dropout": 0.0,
22
+ "auto_map": {
23
+ "AutoConfig": "configuration_phi3.Phi3Config",
24
+ "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
25
+ },
26
+ "bad_words_ids": null,
27
+ "begin_suppress_tokens": null,
28
+ "bos_token_id": 1,
29
+ "chunk_size_feed_forward": 0,
30
+ "cross_attention_hidden_size": null,
31
+ "decoder_start_token_id": null,
32
+ "diversity_penalty": 0.0,
33
+ "do_sample": false,
34
+ "early_stopping": false,
35
+ "embd_pdrop": 0.0,
36
+ "encoder_no_repeat_ngram_size": 0,
37
+ "eos_token_id": 32000,
38
+ "exponential_decay_length_penalty": null,
39
+ "finetuning_task": null,
40
+ "forced_bos_token_id": null,
41
+ "forced_eos_token_id": null,
42
+ "hidden_act": "silu",
43
+ "hidden_size": 3072,
44
+ "id2label": {
45
+ "0": "LABEL_0",
46
+ "1": "LABEL_1"
47
+ },
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": 8192,
50
+ "is_decoder": false,
51
+ "is_encoder_decoder": false,
52
+ "label2id": {
53
+ "LABEL_0": 0,
54
+ "LABEL_1": 1
55
+ },
56
+ "length_penalty": 1.0,
57
+ "max_length": 20,
58
+ "max_position_embeddings": 131072,
59
+ "min_length": 0,
60
+ "model_type": "phi3",
61
+ "no_repeat_ngram_size": 0,
62
+ "num_attention_heads": 32,
63
+ "num_beam_groups": 1,
64
+ "num_beams": 1,
65
+ "num_hidden_layers": 32,
66
+ "num_key_value_heads": 32,
67
+ "num_return_sequences": 1,
68
+ "original_max_position_embeddings": 4096,
69
+ "output_attentions": false,
70
+ "output_hidden_states": false,
71
+ "output_scores": false,
72
+ "pad_token_id": 32000,
73
+ "prefix": null,
74
+ "problem_type": null,
75
+ "pruned_heads": {},
76
+ "remove_invalid_values": false,
77
+ "repetition_penalty": 1.0,
78
+ "resid_pdrop": 0.0,
79
+ "return_dict": true,
80
+ "return_dict_in_generate": false,
81
+ "rms_norm_eps": 1e-05,
82
+ "rope_scaling": {
83
+ "long_factor": [
84
+ 1.0299999713897705,
85
+ 1.0499999523162842,
86
+ 1.0499999523162842,
87
+ 1.0799999237060547,
88
+ 1.2299998998641968,
89
+ 1.2299998998641968,
90
+ 1.2999999523162842,
91
+ 1.4499999284744263,
92
+ 1.5999999046325684,
93
+ 1.6499998569488525,
94
+ 1.8999998569488525,
95
+ 2.859999895095825,
96
+ 3.68999981880188,
97
+ 5.419999599456787,
98
+ 5.489999771118164,
99
+ 5.489999771118164,
100
+ 9.09000015258789,
101
+ 11.579999923706055,
102
+ 15.65999984741211,
103
+ 15.769999504089355,
104
+ 15.789999961853027,
105
+ 18.360000610351562,
106
+ 21.989999771118164,
107
+ 23.079999923706055,
108
+ 30.009998321533203,
109
+ 32.35000228881836,
110
+ 32.590003967285156,
111
+ 35.56000518798828,
112
+ 39.95000457763672,
113
+ 53.840003967285156,
114
+ 56.20000457763672,
115
+ 57.95000457763672,
116
+ 59.29000473022461,
117
+ 59.77000427246094,
118
+ 59.920005798339844,
119
+ 61.190006256103516,
120
+ 61.96000671386719,
121
+ 62.50000762939453,
122
+ 63.3700065612793,
123
+ 63.48000717163086,
124
+ 63.48000717163086,
125
+ 63.66000747680664,
126
+ 63.850006103515625,
127
+ 64.08000946044922,
128
+ 64.760009765625,
129
+ 64.80001068115234,
130
+ 64.81001281738281,
131
+ 64.81001281738281
132
+ ],
133
+ "short_factor": [
134
+ 1.05,
135
+ 1.05,
136
+ 1.05,
137
+ 1.1,
138
+ 1.1,
139
+ 1.1500000000000001,
140
+ 1.2000000000000002,
141
+ 1.2500000000000002,
142
+ 1.3000000000000003,
143
+ 1.3500000000000003,
144
+ 1.5000000000000004,
145
+ 2.000000000000001,
146
+ 2.000000000000001,
147
+ 2.000000000000001,
148
+ 2.000000000000001,
149
+ 2.000000000000001,
150
+ 2.000000000000001,
151
+ 2.000000000000001,
152
+ 2.000000000000001,
153
+ 2.000000000000001,
154
+ 2.000000000000001,
155
+ 2.000000000000001,
156
+ 2.000000000000001,
157
+ 2.000000000000001,
158
+ 2.000000000000001,
159
+ 2.000000000000001,
160
+ 2.000000000000001,
161
+ 2.000000000000001,
162
+ 2.000000000000001,
163
+ 2.000000000000001,
164
+ 2.000000000000001,
165
+ 2.000000000000001,
166
+ 2.0500000000000007,
167
+ 2.0500000000000007,
168
+ 2.0500000000000007,
169
+ 2.1000000000000005,
170
+ 2.1000000000000005,
171
+ 2.1000000000000005,
172
+ 2.1500000000000004,
173
+ 2.1500000000000004,
174
+ 2.3499999999999996,
175
+ 2.549999999999999,
176
+ 2.5999999999999988,
177
+ 2.5999999999999988,
178
+ 2.7499999999999982,
179
+ 2.849999999999998,
180
+ 2.849999999999998,
181
+ 2.9499999999999975
182
+ ],
183
+ "type": "su"
184
+ },
185
+ "rope_theta": 10000.0,
186
+ "sep_token_id": null,
187
+ "sliding_window": 262144,
188
+ "suppress_tokens": null,
189
+ "task_specific_params": null,
190
+ "temperature": 1.0,
191
+ "tf_legacy_loss": false,
192
+ "tie_encoder_decoder": false,
193
+ "tie_word_embeddings": false,
194
+ "tokenizer_class": null,
195
+ "top_k": 50,
196
+ "top_p": 1.0,
197
+ "torch_dtype": "bfloat16",
198
+ "torchscript": false,
199
+ "transformers_version": "4.37.2",
200
+ "typical_p": 1.0,
201
+ "use_bfloat16": true,
202
+ "use_cache": true,
203
+ "vocab_size": 32020
204
+ },
205
+ "max_dynamic_patch": 12,
206
+ "min_dynamic_patch": 1,
207
+ "model_type": "internvl_chat",
208
+ "ps_version": "v2",
209
+ "select_layer": -1,
210
+ "template": "phi3-chat",
211
+ "torch_dtype": "bfloat16",
212
+ "transformers_version": null,
213
+ "use_backbone_lora": 0,
214
+ "use_llm_lora": 0,
215
+ "use_thumbnail": true,
216
+ "vision_config": {
217
+ "_name_or_path": "",
218
+ "add_cross_attention": false,
219
+ "architectures": [
220
+ "InternVisionModel"
221
+ ],
222
+ "attention_dropout": 0.0,
223
+ "bad_words_ids": null,
224
+ "begin_suppress_tokens": null,
225
+ "bos_token_id": null,
226
+ "chunk_size_feed_forward": 0,
227
+ "cross_attention_hidden_size": null,
228
+ "decoder_start_token_id": null,
229
+ "diversity_penalty": 0.0,
230
+ "do_sample": false,
231
+ "drop_path_rate": 0.0,
232
+ "dropout": 0.0,
233
+ "early_stopping": false,
234
+ "encoder_no_repeat_ngram_size": 0,
235
+ "eos_token_id": null,
236
+ "exponential_decay_length_penalty": null,
237
+ "finetuning_task": null,
238
+ "forced_bos_token_id": null,
239
+ "forced_eos_token_id": null,
240
+ "hidden_act": "gelu",
241
+ "hidden_size": 1024,
242
+ "id2label": {
243
+ "0": "LABEL_0",
244
+ "1": "LABEL_1"
245
+ },
246
+ "image_size": 448,
247
+ "initializer_factor": 1.0,
248
+ "initializer_range": 0.02,
249
+ "intermediate_size": 4096,
250
+ "is_decoder": false,
251
+ "is_encoder_decoder": false,
252
+ "label2id": {
253
+ "LABEL_0": 0,
254
+ "LABEL_1": 1
255
+ },
256
+ "layer_norm_eps": 1e-06,
257
+ "length_penalty": 1.0,
258
+ "max_length": 20,
259
+ "min_length": 0,
260
+ "model_type": "intern_vit_6b",
261
+ "no_repeat_ngram_size": 0,
262
+ "norm_type": "layer_norm",
263
+ "num_attention_heads": 16,
264
+ "num_beam_groups": 1,
265
+ "num_beams": 1,
266
+ "num_channels": 3,
267
+ "num_hidden_layers": 24,
268
+ "num_return_sequences": 1,
269
+ "output_attentions": false,
270
+ "output_hidden_states": false,
271
+ "output_scores": false,
272
+ "pad_token_id": null,
273
+ "patch_size": 14,
274
+ "prefix": null,
275
+ "problem_type": null,
276
+ "pruned_heads": {},
277
+ "qk_normalization": false,
278
+ "qkv_bias": true,
279
+ "remove_invalid_values": false,
280
+ "repetition_penalty": 1.0,
281
+ "return_dict": true,
282
+ "return_dict_in_generate": false,
283
+ "sep_token_id": null,
284
+ "suppress_tokens": null,
285
+ "task_specific_params": null,
286
+ "temperature": 1.0,
287
+ "tf_legacy_loss": false,
288
+ "tie_encoder_decoder": false,
289
+ "tie_word_embeddings": true,
290
+ "tokenizer_class": null,
291
+ "top_k": 50,
292
+ "top_p": 1.0,
293
+ "torch_dtype": "bfloat16",
294
+ "torchscript": false,
295
+ "transformers_version": "4.37.2",
296
+ "typical_p": 1.0,
297
+ "use_bfloat16": true,
298
+ "use_flash_attn": true
299
+ }
300
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 2,
5
+ 32000,
6
+ 32007
7
+ ],
8
+ "transformers_version": "4.37.2"
9
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b58788056130d021acf2d12401cf0385c57d016d713e2d07341772a316a689bf
3
+ size 4983255264
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31711513343f4c0ae799d3dc77f2e06273616abdd07e611345d167025acc6c0
3
+ size 3921534432
model.safetensors.index.json ADDED
@@ -0,0 +1,548 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 8904724480
4
+ },
5
+ "weight_map": {
6
+ "language_model.lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "language_model.model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
13
+ "language_model.model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
14
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
15
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
16
+ "language_model.model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
17
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
19
+ "language_model.model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
20
+ "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "language_model.model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "language_model.model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
26
+ "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "language_model.model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
31
+ "language_model.model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
32
+ "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
34
+ "language_model.model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
37
+ "language_model.model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
38
+ "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
40
+ "language_model.model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
41
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
43
+ "language_model.model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
44
+ "language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "language_model.model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "language_model.model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
50
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
51
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
52
+ "language_model.model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
53
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
54
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
55
+ "language_model.model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
56
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
57
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
58
+ "language_model.model.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
59
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
60
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
61
+ "language_model.model.layers.16.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
62
+ "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
63
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
64
+ "language_model.model.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
65
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
66
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
67
+ "language_model.model.layers.17.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
68
+ "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
69
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
70
+ "language_model.model.layers.18.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
71
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
72
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
73
+ "language_model.model.layers.18.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
74
+ "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
75
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
76
+ "language_model.model.layers.19.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
77
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
78
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
79
+ "language_model.model.layers.19.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
80
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "language_model.model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
85
+ "language_model.model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
86
+ "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
87
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
88
+ "language_model.model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
89
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
90
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
91
+ "language_model.model.layers.20.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
92
+ "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
93
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
94
+ "language_model.model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
95
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
96
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
97
+ "language_model.model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
98
+ "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
99
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
100
+ "language_model.model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
101
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
102
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
103
+ "language_model.model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
104
+ "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
105
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
106
+ "language_model.model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
107
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
108
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
109
+ "language_model.model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
110
+ "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
111
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
112
+ "language_model.model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
113
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
114
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
115
+ "language_model.model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
116
+ "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
117
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
118
+ "language_model.model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
119
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
120
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
121
+ "language_model.model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
122
+ "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
123
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
124
+ "language_model.model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
125
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
127
+ "language_model.model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
128
+ "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
129
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
130
+ "language_model.model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
131
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
132
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
133
+ "language_model.model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
134
+ "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
+ "language_model.model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
137
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
138
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
139
+ "language_model.model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
140
+ "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
141
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
142
+ "language_model.model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
143
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
145
+ "language_model.model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
146
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
147
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
148
+ "language_model.model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
149
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
150
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
151
+ "language_model.model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
152
+ "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "language_model.model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
157
+ "language_model.model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
158
+ "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
159
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
160
+ "language_model.model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
161
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
163
+ "language_model.model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
164
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "language_model.model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
167
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
169
+ "language_model.model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
170
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
172
+ "language_model.model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
173
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
174
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
175
+ "language_model.model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
176
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
177
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
178
+ "language_model.model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
179
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
181
+ "language_model.model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
182
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
183
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
184
+ "language_model.model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
185
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
186
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
187
+ "language_model.model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
188
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
+ "language_model.model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
191
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
192
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
193
+ "language_model.model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
194
+ "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
195
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
196
+ "language_model.model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
197
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
199
+ "language_model.model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
200
+ "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
201
+ "mlp1.0.bias": "model-00002-of-00002.safetensors",
202
+ "mlp1.0.weight": "model-00002-of-00002.safetensors",
203
+ "mlp1.1.bias": "model-00002-of-00002.safetensors",
204
+ "mlp1.1.weight": "model-00002-of-00002.safetensors",
205
+ "mlp1.3.bias": "model-00002-of-00002.safetensors",
206
+ "mlp1.3.weight": "model-00002-of-00002.safetensors",
207
+ "vision_model.embeddings.class_embedding": "model-00001-of-00002.safetensors",
208
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00002.safetensors",
209
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
210
+ "vision_model.embeddings.position_embedding": "model-00001-of-00002.safetensors",
211
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00002.safetensors",
212
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00002.safetensors",
213
+ "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
214
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
215
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00002.safetensors",
216
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00002.safetensors",
217
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
218
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
219
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
220
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
221
+ "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00002.safetensors",
222
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00002.safetensors",
223
+ "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00002.safetensors",
224
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00002.safetensors",
225
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00002.safetensors",
226
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00002.safetensors",
227
+ "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
228
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
229
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00002.safetensors",
230
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00002.safetensors",
231
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
232
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
233
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
234
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
235
+ "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00002.safetensors",
236
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00002.safetensors",
237
+ "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00002.safetensors",
238
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00002.safetensors",
239
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00002.safetensors",
240
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00002.safetensors",
241
+ "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
242
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
243
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00002.safetensors",
244
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00002.safetensors",
245
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
246
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
247
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
248
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
249
+ "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00002.safetensors",
250
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00002.safetensors",
251
+ "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00002.safetensors",
252
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00002.safetensors",
253
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00002.safetensors",
254
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00002.safetensors",
255
+ "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
256
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
257
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00002.safetensors",
258
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00002.safetensors",
259
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
260
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
261
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
262
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
263
+ "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00002.safetensors",
264
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00002.safetensors",
265
+ "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00002.safetensors",
266
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00002.safetensors",
267
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00002.safetensors",
268
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00002.safetensors",
269
+ "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
270
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
271
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00002.safetensors",
272
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00002.safetensors",
273
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
274
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
275
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
276
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
277
+ "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00002.safetensors",
278
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00002.safetensors",
279
+ "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00002.safetensors",
280
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00002.safetensors",
281
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00002.safetensors",
282
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00002.safetensors",
283
+ "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
284
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
285
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00002.safetensors",
286
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00002.safetensors",
287
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
288
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
289
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
290
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
291
+ "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00002.safetensors",
292
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00002.safetensors",
293
+ "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00002.safetensors",
294
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00002.safetensors",
295
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00002.safetensors",
296
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00002.safetensors",
297
+ "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
298
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
299
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00002.safetensors",
300
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00002.safetensors",
301
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
302
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
303
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
304
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
305
+ "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00002.safetensors",
306
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00002.safetensors",
307
+ "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00002.safetensors",
308
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00002.safetensors",
309
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00002.safetensors",
310
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00002.safetensors",
311
+ "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
312
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
313
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00002.safetensors",
314
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00002.safetensors",
315
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
316
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
317
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
318
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
319
+ "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00002.safetensors",
320
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00002.safetensors",
321
+ "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00002.safetensors",
322
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00002.safetensors",
323
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00002.safetensors",
324
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00002.safetensors",
325
+ "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
326
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
327
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00002.safetensors",
328
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00002.safetensors",
329
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
330
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
331
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
332
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
333
+ "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00002.safetensors",
334
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00002.safetensors",
335
+ "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00002.safetensors",
336
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00002.safetensors",
337
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00002.safetensors",
338
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00002.safetensors",
339
+ "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
340
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
341
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00002.safetensors",
342
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00002.safetensors",
343
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
344
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
345
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
346
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
347
+ "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00002.safetensors",
348
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00002.safetensors",
349
+ "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00002.safetensors",
350
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00002.safetensors",
351
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00002.safetensors",
352
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00002.safetensors",
353
+ "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
354
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
355
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00002.safetensors",
356
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00002.safetensors",
357
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
358
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
359
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
360
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
361
+ "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00002.safetensors",
362
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00002.safetensors",
363
+ "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00002.safetensors",
364
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00002.safetensors",
365
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00002.safetensors",
366
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00002.safetensors",
367
+ "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
368
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
369
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00002.safetensors",
370
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00002.safetensors",
371
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
372
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
373
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
374
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
375
+ "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00002.safetensors",
376
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00002.safetensors",
377
+ "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00002.safetensors",
378
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00002.safetensors",
379
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00002.safetensors",
380
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00002.safetensors",
381
+ "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
382
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
383
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00002.safetensors",
384
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00002.safetensors",
385
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
386
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
387
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
388
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
389
+ "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00002.safetensors",
390
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00002.safetensors",
391
+ "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00002.safetensors",
392
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00002.safetensors",
393
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00002.safetensors",
394
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00002.safetensors",
395
+ "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
396
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
397
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00002.safetensors",
398
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00002.safetensors",
399
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
400
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
401
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
402
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
403
+ "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00002.safetensors",
404
+ "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00002.safetensors",
405
+ "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00002.safetensors",
406
+ "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00002.safetensors",
407
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00002.safetensors",
408
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00002.safetensors",
409
+ "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
410
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
411
+ "vision_model.encoder.layers.21.ls1": "model-00001-of-00002.safetensors",
412
+ "vision_model.encoder.layers.21.ls2": "model-00001-of-00002.safetensors",
413
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
414
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
415
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
416
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
417
+ "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00002.safetensors",
418
+ "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00002.safetensors",
419
+ "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00002.safetensors",
420
+ "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00002.safetensors",
421
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00002.safetensors",
422
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00002.safetensors",
423
+ "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
424
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
425
+ "vision_model.encoder.layers.22.ls1": "model-00001-of-00002.safetensors",
426
+ "vision_model.encoder.layers.22.ls2": "model-00001-of-00002.safetensors",
427
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
428
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
429
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
430
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
431
+ "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00002.safetensors",
432
+ "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00002.safetensors",
433
+ "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00002.safetensors",
434
+ "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00002.safetensors",
435
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00002.safetensors",
436
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00002.safetensors",
437
+ "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
438
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
439
+ "vision_model.encoder.layers.23.ls1": "model-00001-of-00002.safetensors",
440
+ "vision_model.encoder.layers.23.ls2": "model-00001-of-00002.safetensors",
441
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
442
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
443
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
444
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
445
+ "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00002.safetensors",
446
+ "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00002.safetensors",
447
+ "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00002.safetensors",
448
+ "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00002.safetensors",
449
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00002.safetensors",
450
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00002.safetensors",
451
+ "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
452
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
453
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00002.safetensors",
454
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00002.safetensors",
455
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
456
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
457
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
458
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
459
+ "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00002.safetensors",
460
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00002.safetensors",
461
+ "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00002.safetensors",
462
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00002.safetensors",
463
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00002.safetensors",
464
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00002.safetensors",
465
+ "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
466
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
467
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00002.safetensors",
468
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00002.safetensors",
469
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
470
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
471
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
472
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
473
+ "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00002.safetensors",
474
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00002.safetensors",
475
+ "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00002.safetensors",
476
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00002.safetensors",
477
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00002.safetensors",
478
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00002.safetensors",
479
+ "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
480
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
481
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00002.safetensors",
482
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00002.safetensors",
483
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
484
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
485
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
486
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
487
+ "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00002.safetensors",
488
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00002.safetensors",
489
+ "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00002.safetensors",
490
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00002.safetensors",
491
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00002.safetensors",
492
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00002.safetensors",
493
+ "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
494
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
495
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00002.safetensors",
496
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00002.safetensors",
497
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
498
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
499
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
500
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
501
+ "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00002.safetensors",
502
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00002.safetensors",
503
+ "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00002.safetensors",
504
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00002.safetensors",
505
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00002.safetensors",
506
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00002.safetensors",
507
+ "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
508
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
509
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00002.safetensors",
510
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00002.safetensors",
511
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
512
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
513
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
514
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
515
+ "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00002.safetensors",
516
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00002.safetensors",
517
+ "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00002.safetensors",
518
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00002.safetensors",
519
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00002.safetensors",
520
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00002.safetensors",
521
+ "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
522
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
523
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00002.safetensors",
524
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00002.safetensors",
525
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
526
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
527
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
528
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
529
+ "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00002.safetensors",
530
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00002.safetensors",
531
+ "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00002.safetensors",
532
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00002.safetensors",
533
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00002.safetensors",
534
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00002.safetensors",
535
+ "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
536
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
537
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00002.safetensors",
538
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00002.safetensors",
539
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
540
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
541
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
542
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
543
+ "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00002.safetensors",
544
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00002.safetensors",
545
+ "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00002.safetensors",
546
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00002.safetensors"
547
+ }
548
+ }