Hugging Face's logo

TIGER-Lab
/
VideoScore

Visual Question Answering
Transformers
Safetensors
English
idefics2
text-classification
text-generation-inference
Inference Endpoints
Model card Files Community
hexuan21 commited on
Commit
5edbd03
•
0 Parent(s):

Duplicate from Mantis-VL/mantis-8b-idefics2-video-eval-anno-real_4096_regression

Browse files
Files changed (16) hide show
  1. .gitattributes +35 -0
  2. added_tokens.json +5 -0
  3. config.json +248 -0
  4. generation_config.json +18 -0
  5. model-00001-of-00004.safetensors +3 -0
  6. model-00002-of-00004.safetensors +3 -0
  7. model-00003-of-00004.safetensors +3 -0
  8. model-00004-of-00004.safetensors +3 -0
  9. model.safetensors.index.json +771 -0
  10. preprocessor_config.json +26 -0
  11. processor_config.json +4 -0
  12. special_tokens_map.json +53 -0
  13. tokenizer.json +0 -0
  14. tokenizer.model +3 -0
  15. tokenizer_config.json +72 -0
  16. training_args.bin +3 -0
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<end_of_utterance>": 32002,
3
+ "<fake_token_around_image>": 32000,
4
+ "<image>": 32001
5
+ }
config.json ADDED
@@ -0,0 +1,248 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "TIGER-Lab/Mantis-8B-Idefics2",
3
+ "architectures": [
4
+ "Idefics2ForSequenceClassification"
5
+ ],
6
+ "id2label": {
7
+ "0": "LABEL_0",
8
+ "1": "LABEL_1",
9
+ "2": "LABEL_2",
10
+ "3": "LABEL_3",
11
+ "4": "LABEL_4"
12
+ },
13
+ "image_token_id": 32001,
14
+ "label2id": {
15
+ "LABEL_0": 0,
16
+ "LABEL_1": 1,
17
+ "LABEL_2": 2,
18
+ "LABEL_3": 3,
19
+ "LABEL_4": 4
20
+ },
21
+ "model_type": "idefics2",
22
+ "perceiver_config": {
23
+ "_name_or_path": "",
24
+ "add_cross_attention": false,
25
+ "architectures": null,
26
+ "attention_dropout": 0.0,
27
+ "bad_words_ids": null,
28
+ "begin_suppress_tokens": null,
29
+ "bos_token_id": null,
30
+ "chunk_size_feed_forward": 0,
31
+ "cross_attention_hidden_size": null,
32
+ "decoder_start_token_id": null,
33
+ "diversity_penalty": 0.0,
34
+ "do_sample": false,
35
+ "early_stopping": false,
36
+ "encoder_no_repeat_ngram_size": 0,
37
+ "eos_token_id": null,
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
+ "id2label": {
44
+ "0": "LABEL_0",
45
+ "1": "LABEL_1"
46
+ },
47
+ "is_decoder": false,
48
+ "is_encoder_decoder": false,
49
+ "label2id": {
50
+ "LABEL_0": 0,
51
+ "LABEL_1": 1
52
+ },
53
+ "length_penalty": 1.0,
54
+ "max_length": 20,
55
+ "min_length": 0,
56
+ "model_type": "idefics2",
57
+ "no_repeat_ngram_size": 0,
58
+ "num_beam_groups": 1,
59
+ "num_beams": 1,
60
+ "num_key_value_heads": 4,
61
+ "num_return_sequences": 1,
62
+ "output_attentions": false,
63
+ "output_hidden_states": false,
64
+ "output_scores": false,
65
+ "pad_token_id": null,
66
+ "prefix": null,
67
+ "problem_type": null,
68
+ "pruned_heads": {},
69
+ "remove_invalid_values": false,
70
+ "repetition_penalty": 1.0,
71
+ "resampler_depth": 3,
72
+ "resampler_head_dim": 96,
73
+ "resampler_n_heads": 16,
74
+ "resampler_n_latents": 64,
75
+ "return_dict": true,
76
+ "return_dict_in_generate": false,
77
+ "sep_token_id": null,
78
+ "suppress_tokens": null,
79
+ "task_specific_params": null,
80
+ "temperature": 1.0,
81
+ "tf_legacy_loss": false,
82
+ "tie_encoder_decoder": false,
83
+ "tie_word_embeddings": true,
84
+ "tokenizer_class": null,
85
+ "top_k": 50,
86
+ "top_p": 1.0,
87
+ "torch_dtype": null,
88
+ "torchscript": false,
89
+ "typical_p": 1.0,
90
+ "use_bfloat16": false
91
+ },
92
+ "problem_type": "regression",
93
+ "text_config": {
94
+ "_name_or_path": "",
95
+ "add_cross_attention": false,
96
+ "architectures": null,
97
+ "attention_dropout": 0.0,
98
+ "bad_words_ids": null,
99
+ "begin_suppress_tokens": null,
100
+ "bos_token_id": 1,
101
+ "chunk_size_feed_forward": 0,
102
+ "cross_attention_hidden_size": null,
103
+ "decoder_start_token_id": null,
104
+ "diversity_penalty": 0.0,
105
+ "do_sample": false,
106
+ "early_stopping": false,
107
+ "encoder_no_repeat_ngram_size": 0,
108
+ "eos_token_id": 2,
109
+ "exponential_decay_length_penalty": null,
110
+ "finetuning_task": null,
111
+ "forced_bos_token_id": null,
112
+ "forced_eos_token_id": null,
113
+ "hidden_act": "silu",
114
+ "hidden_size": 4096,
115
+ "id2label": {
116
+ "0": "LABEL_0",
117
+ "1": "LABEL_1"
118
+ },
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 14336,
121
+ "is_decoder": false,
122
+ "is_encoder_decoder": false,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1
126
+ },
127
+ "length_penalty": 1.0,
128
+ "max_length": 20,
129
+ "max_position_embeddings": 32768,
130
+ "min_length": 0,
131
+ "model_type": "mistral",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 32,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_hidden_layers": 32,
137
+ "num_key_value_heads": 8,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_scores": false,
142
+ "pad_token_id": 0,
143
+ "prefix": null,
144
+ "problem_type": null,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "rms_norm_eps": 1e-05,
151
+ "rope_theta": 10000.0,
152
+ "sep_token_id": null,
153
+ "sliding_window": 4096,
154
+ "suppress_tokens": null,
155
+ "task_specific_params": null,
156
+ "temperature": 1.0,
157
+ "tf_legacy_loss": false,
158
+ "tie_encoder_decoder": false,
159
+ "tie_word_embeddings": false,
160
+ "tokenizer_class": null,
161
+ "top_k": 50,
162
+ "top_p": 1.0,
163
+ "torch_dtype": null,
164
+ "torchscript": false,
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false,
167
+ "use_cache": true,
168
+ "vocab_size": 32003
169
+ },
170
+ "tie_word_embeddings": false,
171
+ "torch_dtype": "bfloat16",
172
+ "transformers_version": "4.41.1",
173
+ "use_cache": true,
174
+ "vision_config": {
175
+ "_name_or_path": "",
176
+ "add_cross_attention": false,
177
+ "architectures": null,
178
+ "attention_dropout": 0.0,
179
+ "bad_words_ids": null,
180
+ "begin_suppress_tokens": null,
181
+ "bos_token_id": null,
182
+ "chunk_size_feed_forward": 0,
183
+ "cross_attention_hidden_size": null,
184
+ "decoder_start_token_id": null,
185
+ "diversity_penalty": 0.0,
186
+ "do_sample": false,
187
+ "early_stopping": false,
188
+ "encoder_no_repeat_ngram_size": 0,
189
+ "eos_token_id": null,
190
+ "exponential_decay_length_penalty": null,
191
+ "finetuning_task": null,
192
+ "forced_bos_token_id": null,
193
+ "forced_eos_token_id": null,
194
+ "hidden_act": "gelu_pytorch_tanh",
195
+ "hidden_size": 1152,
196
+ "id2label": {
197
+ "0": "LABEL_0",
198
+ "1": "LABEL_1"
199
+ },
200
+ "image_size": 980,
201
+ "initializer_range": 0.02,
202
+ "intermediate_size": 4304,
203
+ "is_decoder": false,
204
+ "is_encoder_decoder": false,
205
+ "label2id": {
206
+ "LABEL_0": 0,
207
+ "LABEL_1": 1
208
+ },
209
+ "layer_norm_eps": 1e-06,
210
+ "length_penalty": 1.0,
211
+ "max_length": 20,
212
+ "min_length": 0,
213
+ "model_type": "idefics2",
214
+ "no_repeat_ngram_size": 0,
215
+ "num_attention_heads": 16,
216
+ "num_beam_groups": 1,
217
+ "num_beams": 1,
218
+ "num_channels": 3,
219
+ "num_hidden_layers": 27,
220
+ "num_return_sequences": 1,
221
+ "output_attentions": false,
222
+ "output_hidden_states": false,
223
+ "output_scores": false,
224
+ "pad_token_id": null,
225
+ "patch_size": 14,
226
+ "prefix": null,
227
+ "problem_type": null,
228
+ "pruned_heads": {},
229
+ "remove_invalid_values": false,
230
+ "repetition_penalty": 1.0,
231
+ "return_dict": true,
232
+ "return_dict_in_generate": false,
233
+ "sep_token_id": null,
234
+ "suppress_tokens": null,
235
+ "task_specific_params": null,
236
+ "temperature": 1.0,
237
+ "tf_legacy_loss": false,
238
+ "tie_encoder_decoder": false,
239
+ "tie_word_embeddings": true,
240
+ "tokenizer_class": null,
241
+ "top_k": 50,
242
+ "top_p": 1.0,
243
+ "torch_dtype": null,
244
+ "torchscript": false,
245
+ "typical_p": 1.0,
246
+ "use_bfloat16": false
247
+ }
248
+ }
generation_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 32000
6
+ ],
7
+ [
8
+ 32001
9
+ ]
10
+ ],
11
+ "bos_token_id": 1,
12
+ "eos_token_id": [
13
+ 2,
14
+ 32002
15
+ ],
16
+ "pad_token_id": 0,
17
+ "transformers_version": "4.41.1"
18
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad0c362b5959d57d98000e7adc9dc1bb9eaa3c55d972ba0bb22c8a60a993f52
3
+ size 4966706832
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec11d9f932bd903970aa43bdb877ea6d820e8416c2b3cc979fb7313c6f2236c
3
+ size 4915917232
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4864868c65c3b787862aab0afa7642337dce0382d2ab67ba4bc2ec8ba357400
3
+ size 4999820504
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e95f26bbd751259ecf72afffcd8fde8c532a23cfbf7e642ec981d685abbc5ac
3
+ size 1661063426
model.safetensors.index.json ADDED
@@ -0,0 +1,771 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16543408618
4
+ },
5
+ "weight_map": {
6
+ "model.connector.modality_projection.down_proj.weight": "model-00001-of-00004.safetensors",
7
+ "model.connector.modality_projection.gate_proj.weight": "model-00001-of-00004.safetensors",
8
+ "model.connector.modality_projection.up_proj.weight": "model-00001-of-00004.safetensors",
9
+ "model.connector.perceiver_resampler.latents": "model-00001-of-00004.safetensors",
10
+ "model.connector.perceiver_resampler.layers.0.input_context_norm.weight": "model-00001-of-00004.safetensors",
11
+ "model.connector.perceiver_resampler.layers.0.input_latents_norm.weight": "model-00001-of-00004.safetensors",
12
+ "model.connector.perceiver_resampler.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
13
+ "model.connector.perceiver_resampler.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.connector.perceiver_resampler.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.connector.perceiver_resampler.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
16
+ "model.connector.perceiver_resampler.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.connector.perceiver_resampler.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
18
+ "model.connector.perceiver_resampler.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.connector.perceiver_resampler.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.connector.perceiver_resampler.layers.1.input_context_norm.weight": "model-00001-of-00004.safetensors",
21
+ "model.connector.perceiver_resampler.layers.1.input_latents_norm.weight": "model-00001-of-00004.safetensors",
22
+ "model.connector.perceiver_resampler.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.connector.perceiver_resampler.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.connector.perceiver_resampler.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.connector.perceiver_resampler.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
26
+ "model.connector.perceiver_resampler.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "model.connector.perceiver_resampler.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "model.connector.perceiver_resampler.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
29
+ "model.connector.perceiver_resampler.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
30
+ "model.connector.perceiver_resampler.layers.2.input_context_norm.weight": "model-00001-of-00004.safetensors",
31
+ "model.connector.perceiver_resampler.layers.2.input_latents_norm.weight": "model-00001-of-00004.safetensors",
32
+ "model.connector.perceiver_resampler.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
33
+ "model.connector.perceiver_resampler.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
34
+ "model.connector.perceiver_resampler.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
35
+ "model.connector.perceiver_resampler.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
36
+ "model.connector.perceiver_resampler.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
37
+ "model.connector.perceiver_resampler.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
38
+ "model.connector.perceiver_resampler.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
39
+ "model.connector.perceiver_resampler.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
40
+ "model.connector.perceiver_resampler.norm.weight": "model-00001-of-00004.safetensors",
41
+ "model.text_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
42
+ "model.text_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
43
+ "model.text_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
44
+ "model.text_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
45
+ "model.text_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
46
+ "model.text_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
47
+ "model.text_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
48
+ "model.text_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
49
+ "model.text_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
50
+ "model.text_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
51
+ "model.text_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
52
+ "model.text_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
53
+ "model.text_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
54
+ "model.text_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
55
+ "model.text_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
56
+ "model.text_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
57
+ "model.text_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
58
+ "model.text_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
59
+ "model.text_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
60
+ "model.text_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "model.text_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.text_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
63
+ "model.text_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.text_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
65
+ "model.text_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.text_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
67
+ "model.text_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.text_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.text_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
70
+ "model.text_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.text_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
72
+ "model.text_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.text_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
74
+ "model.text_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.text_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "model.text_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.text_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.text_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
79
+ "model.text_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.text_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
81
+ "model.text_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.text_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
83
+ "model.text_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.text_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
85
+ "model.text_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.text_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.text_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
88
+ "model.text_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.text_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
90
+ "model.text_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.text_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
92
+ "model.text_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.text_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
94
+ "model.text_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.text_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.text_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "model.text_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.text_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
99
+ "model.text_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.text_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
101
+ "model.text_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.text_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
103
+ "model.text_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.text_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.text_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
106
+ "model.text_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.text_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
108
+ "model.text_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.text_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
110
+ "model.text_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.text_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "model.text_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.text_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.text_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
115
+ "model.text_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
116
+ "model.text_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
117
+ "model.text_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
118
+ "model.text_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
119
+ "model.text_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
120
+ "model.text_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
121
+ "model.text_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
122
+ "model.text_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
123
+ "model.text_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
124
+ "model.text_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
125
+ "model.text_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
126
+ "model.text_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.text_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
128
+ "model.text_model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.text_model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
130
+ "model.text_model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.text_model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.text_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "model.text_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.text_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
135
+ "model.text_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.text_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
137
+ "model.text_model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.text_model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
139
+ "model.text_model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.text_model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.text_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
142
+ "model.text_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.text_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
144
+ "model.text_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.text_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
146
+ "model.text_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.text_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "model.text_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.text_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.text_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
151
+ "model.text_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
152
+ "model.text_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
153
+ "model.text_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
154
+ "model.text_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
155
+ "model.text_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
156
+ "model.text_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
157
+ "model.text_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
158
+ "model.text_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
159
+ "model.text_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
160
+ "model.text_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.text_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
162
+ "model.text_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.text_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
164
+ "model.text_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.text_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
166
+ "model.text_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.text_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.text_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "model.text_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.text_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
171
+ "model.text_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.text_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
173
+ "model.text_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.text_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
175
+ "model.text_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.text_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.text_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
178
+ "model.text_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.text_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
180
+ "model.text_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.text_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
182
+ "model.text_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.text_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "model.text_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.text_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.text_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
187
+ "model.text_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.text_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
189
+ "model.text_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.text_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
191
+ "model.text_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.text_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
193
+ "model.text_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.text_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.text_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
196
+ "model.text_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.text_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
198
+ "model.text_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.text_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
200
+ "model.text_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.text_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
202
+ "model.text_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.text_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.text_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "model.text_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.text_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
207
+ "model.text_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.text_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
209
+ "model.text_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.text_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
211
+ "model.text_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.text_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.text_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
214
+ "model.text_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.text_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
216
+ "model.text_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
217
+ "model.text_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
218
+ "model.text_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "model.text_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "model.text_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
221
+ "model.text_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
222
+ "model.text_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
223
+ "model.text_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
224
+ "model.text_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
225
+ "model.text_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.text_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
227
+ "model.text_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.text_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
229
+ "model.text_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.text_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.text_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
232
+ "model.text_model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
233
+ "model.text_model.layers.28.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
234
+ "model.text_model.layers.28.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.text_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
236
+ "model.text_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.text_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
238
+ "model.text_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.text_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.text_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
241
+ "model.text_model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
242
+ "model.text_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
243
+ "model.text_model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
244
+ "model.text_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
245
+ "model.text_model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
246
+ "model.text_model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
247
+ "model.text_model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
248
+ "model.text_model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
249
+ "model.text_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
250
+ "model.text_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.text_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
252
+ "model.text_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.text_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
254
+ "model.text_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.text_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
256
+ "model.text_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.text_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.text_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
259
+ "model.text_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
260
+ "model.text_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
261
+ "model.text_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
262
+ "model.text_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
263
+ "model.text_model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
264
+ "model.text_model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
265
+ "model.text_model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
266
+ "model.text_model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
267
+ "model.text_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
268
+ "model.text_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
269
+ "model.text_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
270
+ "model.text_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
271
+ "model.text_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
272
+ "model.text_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
273
+ "model.text_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
274
+ "model.text_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
275
+ "model.text_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
276
+ "model.text_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "model.text_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.text_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
279
+ "model.text_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.text_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
281
+ "model.text_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.text_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
283
+ "model.text_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.text_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.text_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
286
+ "model.text_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
287
+ "model.text_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
288
+ "model.text_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.text_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
290
+ "model.text_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "model.text_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "model.text_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
293
+ "model.text_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
294
+ "model.text_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
295
+ "model.text_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.text_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
297
+ "model.text_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
298
+ "model.text_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
299
+ "model.text_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
300
+ "model.text_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
301
+ "model.text_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
302
+ "model.text_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
303
+ "model.text_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
304
+ "model.text_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
305
+ "model.text_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
306
+ "model.text_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
307
+ "model.text_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
308
+ "model.text_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
309
+ "model.text_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
310
+ "model.text_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
311
+ "model.text_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
312
+ "model.text_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
313
+ "model.text_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
314
+ "model.text_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
315
+ "model.text_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
316
+ "model.text_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
317
+ "model.text_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
318
+ "model.text_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
319
+ "model.text_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
320
+ "model.text_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
321
+ "model.text_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
322
+ "model.text_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
323
+ "model.text_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
324
+ "model.text_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
325
+ "model.text_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
326
+ "model.text_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
327
+ "model.text_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
328
+ "model.text_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
329
+ "model.text_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
330
+ "model.text_model.norm.weight": "model-00004-of-00004.safetensors",
331
+ "model.vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
332
+ "model.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
333
+ "model.vision_model.embeddings.position_embedding.weight": "model-00001-of-00004.safetensors",
334
+ "model.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00004.safetensors",
335
+ "model.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00004.safetensors",
336
+ "model.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00004.safetensors",
337
+ "model.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00004.safetensors",
338
+ "model.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
339
+ "model.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
340
+ "model.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
341
+ "model.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
342
+ "model.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
343
+ "model.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
344
+ "model.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
345
+ "model.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
346
+ "model.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
347
+ "model.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
348
+ "model.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
349
+ "model.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
350
+ "model.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00004.safetensors",
351
+ "model.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00004.safetensors",
352
+ "model.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00004.safetensors",
353
+ "model.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00004.safetensors",
354
+ "model.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
355
+ "model.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
356
+ "model.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
357
+ "model.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
358
+ "model.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
359
+ "model.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
360
+ "model.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
361
+ "model.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
362
+ "model.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
363
+ "model.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
364
+ "model.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
365
+ "model.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
366
+ "model.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00004.safetensors",
367
+ "model.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00004.safetensors",
368
+ "model.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00004.safetensors",
369
+ "model.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00004.safetensors",
370
+ "model.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
371
+ "model.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
372
+ "model.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
373
+ "model.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
374
+ "model.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
375
+ "model.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
376
+ "model.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
377
+ "model.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
378
+ "model.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
379
+ "model.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
380
+ "model.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
381
+ "model.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
382
+ "model.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00004.safetensors",
383
+ "model.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00004.safetensors",
384
+ "model.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00004.safetensors",
385
+ "model.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00004.safetensors",
386
+ "model.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
387
+ "model.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
388
+ "model.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
389
+ "model.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
390
+ "model.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
391
+ "model.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
392
+ "model.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
393
+ "model.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
394
+ "model.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
395
+ "model.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
396
+ "model.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
397
+ "model.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
398
+ "model.vision_model.encoder.layers.12.layer_norm1.bias": "model-00001-of-00004.safetensors",
399
+ "model.vision_model.encoder.layers.12.layer_norm1.weight": "model-00001-of-00004.safetensors",
400
+ "model.vision_model.encoder.layers.12.layer_norm2.bias": "model-00001-of-00004.safetensors",
401
+ "model.vision_model.encoder.layers.12.layer_norm2.weight": "model-00001-of-00004.safetensors",
402
+ "model.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
403
+ "model.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
404
+ "model.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
405
+ "model.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
406
+ "model.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
407
+ "model.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
408
+ "model.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
409
+ "model.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
410
+ "model.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
411
+ "model.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
412
+ "model.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
413
+ "model.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
414
+ "model.vision_model.encoder.layers.13.layer_norm1.bias": "model-00001-of-00004.safetensors",
415
+ "model.vision_model.encoder.layers.13.layer_norm1.weight": "model-00001-of-00004.safetensors",
416
+ "model.vision_model.encoder.layers.13.layer_norm2.bias": "model-00001-of-00004.safetensors",
417
+ "model.vision_model.encoder.layers.13.layer_norm2.weight": "model-00001-of-00004.safetensors",
418
+ "model.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
419
+ "model.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
420
+ "model.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
421
+ "model.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
422
+ "model.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
423
+ "model.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
424
+ "model.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
425
+ "model.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
426
+ "model.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
427
+ "model.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
428
+ "model.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
429
+ "model.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
430
+ "model.vision_model.encoder.layers.14.layer_norm1.bias": "model-00001-of-00004.safetensors",
431
+ "model.vision_model.encoder.layers.14.layer_norm1.weight": "model-00001-of-00004.safetensors",
432
+ "model.vision_model.encoder.layers.14.layer_norm2.bias": "model-00001-of-00004.safetensors",
433
+ "model.vision_model.encoder.layers.14.layer_norm2.weight": "model-00001-of-00004.safetensors",
434
+ "model.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
435
+ "model.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
436
+ "model.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
437
+ "model.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
438
+ "model.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
439
+ "model.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
440
+ "model.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
441
+ "model.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
442
+ "model.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
443
+ "model.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
444
+ "model.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
445
+ "model.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
446
+ "model.vision_model.encoder.layers.15.layer_norm1.bias": "model-00001-of-00004.safetensors",
447
+ "model.vision_model.encoder.layers.15.layer_norm1.weight": "model-00001-of-00004.safetensors",
448
+ "model.vision_model.encoder.layers.15.layer_norm2.bias": "model-00001-of-00004.safetensors",
449
+ "model.vision_model.encoder.layers.15.layer_norm2.weight": "model-00001-of-00004.safetensors",
450
+ "model.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
451
+ "model.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
452
+ "model.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
453
+ "model.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
454
+ "model.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
455
+ "model.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
456
+ "model.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
457
+ "model.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
458
+ "model.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
459
+ "model.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
460
+ "model.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
461
+ "model.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
462
+ "model.vision_model.encoder.layers.16.layer_norm1.bias": "model-00001-of-00004.safetensors",
463
+ "model.vision_model.encoder.layers.16.layer_norm1.weight": "model-00001-of-00004.safetensors",
464
+ "model.vision_model.encoder.layers.16.layer_norm2.bias": "model-00001-of-00004.safetensors",
465
+ "model.vision_model.encoder.layers.16.layer_norm2.weight": "model-00001-of-00004.safetensors",
466
+ "model.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
467
+ "model.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
468
+ "model.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
469
+ "model.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
470
+ "model.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
471
+ "model.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
472
+ "model.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
473
+ "model.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
474
+ "model.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
475
+ "model.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
476
+ "model.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
477
+ "model.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
478
+ "model.vision_model.encoder.layers.17.layer_norm1.bias": "model-00001-of-00004.safetensors",
479
+ "model.vision_model.encoder.layers.17.layer_norm1.weight": "model-00001-of-00004.safetensors",
480
+ "model.vision_model.encoder.layers.17.layer_norm2.bias": "model-00001-of-00004.safetensors",
481
+ "model.vision_model.encoder.layers.17.layer_norm2.weight": "model-00001-of-00004.safetensors",
482
+ "model.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
483
+ "model.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
484
+ "model.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
485
+ "model.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
486
+ "model.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
487
+ "model.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
488
+ "model.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
489
+ "model.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
490
+ "model.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
491
+ "model.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
492
+ "model.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
493
+ "model.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
494
+ "model.vision_model.encoder.layers.18.layer_norm1.bias": "model-00001-of-00004.safetensors",
495
+ "model.vision_model.encoder.layers.18.layer_norm1.weight": "model-00001-of-00004.safetensors",
496
+ "model.vision_model.encoder.layers.18.layer_norm2.bias": "model-00001-of-00004.safetensors",
497
+ "model.vision_model.encoder.layers.18.layer_norm2.weight": "model-00001-of-00004.safetensors",
498
+ "model.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
499
+ "model.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
500
+ "model.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
501
+ "model.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
502
+ "model.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
503
+ "model.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
504
+ "model.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
505
+ "model.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
506
+ "model.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
507
+ "model.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
508
+ "model.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
509
+ "model.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
510
+ "model.vision_model.encoder.layers.19.layer_norm1.bias": "model-00001-of-00004.safetensors",
511
+ "model.vision_model.encoder.layers.19.layer_norm1.weight": "model-00001-of-00004.safetensors",
512
+ "model.vision_model.encoder.layers.19.layer_norm2.bias": "model-00001-of-00004.safetensors",
513
+ "model.vision_model.encoder.layers.19.layer_norm2.weight": "model-00001-of-00004.safetensors",
514
+ "model.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
515
+ "model.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
516
+ "model.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
517
+ "model.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
518
+ "model.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
519
+ "model.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
520
+ "model.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
521
+ "model.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
522
+ "model.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
523
+ "model.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
524
+ "model.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
525
+ "model.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
526
+ "model.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00004.safetensors",
527
+ "model.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00004.safetensors",
528
+ "model.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00004.safetensors",
529
+ "model.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00004.safetensors",
530
+ "model.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
531
+ "model.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
532
+ "model.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
533
+ "model.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
534
+ "model.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
535
+ "model.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
536
+ "model.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
537
+ "model.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
538
+ "model.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
539
+ "model.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
540
+ "model.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
541
+ "model.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
542
+ "model.vision_model.encoder.layers.20.layer_norm1.bias": "model-00001-of-00004.safetensors",
543
+ "model.vision_model.encoder.layers.20.layer_norm1.weight": "model-00001-of-00004.safetensors",
544
+ "model.vision_model.encoder.layers.20.layer_norm2.bias": "model-00001-of-00004.safetensors",
545
+ "model.vision_model.encoder.layers.20.layer_norm2.weight": "model-00001-of-00004.safetensors",
546
+ "model.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
547
+ "model.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
548
+ "model.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
549
+ "model.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
550
+ "model.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
551
+ "model.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
552
+ "model.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
553
+ "model.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
554
+ "model.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
555
+ "model.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
556
+ "model.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
557
+ "model.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
558
+ "model.vision_model.encoder.layers.21.layer_norm1.bias": "model-00001-of-00004.safetensors",
559
+ "model.vision_model.encoder.layers.21.layer_norm1.weight": "model-00001-of-00004.safetensors",
560
+ "model.vision_model.encoder.layers.21.layer_norm2.bias": "model-00001-of-00004.safetensors",
561
+ "model.vision_model.encoder.layers.21.layer_norm2.weight": "model-00001-of-00004.safetensors",
562
+ "model.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
563
+ "model.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
564
+ "model.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
565
+ "model.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
566
+ "model.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
567
+ "model.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
568
+ "model.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
569
+ "model.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
570
+ "model.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
571
+ "model.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
572
+ "model.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
573
+ "model.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
574
+ "model.vision_model.encoder.layers.22.layer_norm1.bias": "model-00001-of-00004.safetensors",
575
+ "model.vision_model.encoder.layers.22.layer_norm1.weight": "model-00001-of-00004.safetensors",
576
+ "model.vision_model.encoder.layers.22.layer_norm2.bias": "model-00001-of-00004.safetensors",
577
+ "model.vision_model.encoder.layers.22.layer_norm2.weight": "model-00001-of-00004.safetensors",
578
+ "model.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
579
+ "model.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
580
+ "model.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
581
+ "model.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
582
+ "model.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
583
+ "model.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
584
+ "model.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
585
+ "model.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
586
+ "model.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
587
+ "model.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
588
+ "model.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
589
+ "model.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
590
+ "model.vision_model.encoder.layers.23.layer_norm1.bias": "model-00001-of-00004.safetensors",
591
+ "model.vision_model.encoder.layers.23.layer_norm1.weight": "model-00001-of-00004.safetensors",
592
+ "model.vision_model.encoder.layers.23.layer_norm2.bias": "model-00001-of-00004.safetensors",
593
+ "model.vision_model.encoder.layers.23.layer_norm2.weight": "model-00001-of-00004.safetensors",
594
+ "model.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
595
+ "model.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
596
+ "model.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
597
+ "model.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
598
+ "model.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
599
+ "model.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
600
+ "model.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
601
+ "model.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
602
+ "model.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
603
+ "model.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
604
+ "model.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
605
+ "model.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
606
+ "model.vision_model.encoder.layers.24.layer_norm1.bias": "model-00001-of-00004.safetensors",
607
+ "model.vision_model.encoder.layers.24.layer_norm1.weight": "model-00001-of-00004.safetensors",
608
+ "model.vision_model.encoder.layers.24.layer_norm2.bias": "model-00001-of-00004.safetensors",
609
+ "model.vision_model.encoder.layers.24.layer_norm2.weight": "model-00001-of-00004.safetensors",
610
+ "model.vision_model.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00004.safetensors",
611
+ "model.vision_model.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00004.safetensors",
612
+ "model.vision_model.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00004.safetensors",
613
+ "model.vision_model.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00004.safetensors",
614
+ "model.vision_model.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
615
+ "model.vision_model.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
616
+ "model.vision_model.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
617
+ "model.vision_model.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
618
+ "model.vision_model.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
619
+ "model.vision_model.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
620
+ "model.vision_model.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
621
+ "model.vision_model.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
622
+ "model.vision_model.encoder.layers.25.layer_norm1.bias": "model-00001-of-00004.safetensors",
623
+ "model.vision_model.encoder.layers.25.layer_norm1.weight": "model-00001-of-00004.safetensors",
624
+ "model.vision_model.encoder.layers.25.layer_norm2.bias": "model-00001-of-00004.safetensors",
625
+ "model.vision_model.encoder.layers.25.layer_norm2.weight": "model-00001-of-00004.safetensors",
626
+ "model.vision_model.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00004.safetensors",
627
+ "model.vision_model.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00004.safetensors",
628
+ "model.vision_model.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00004.safetensors",
629
+ "model.vision_model.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00004.safetensors",
630
+ "model.vision_model.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
631
+ "model.vision_model.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
632
+ "model.vision_model.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
633
+ "model.vision_model.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
634
+ "model.vision_model.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
635
+ "model.vision_model.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
636
+ "model.vision_model.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
637
+ "model.vision_model.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
638
+ "model.vision_model.encoder.layers.26.layer_norm1.bias": "model-00001-of-00004.safetensors",
639
+ "model.vision_model.encoder.layers.26.layer_norm1.weight": "model-00001-of-00004.safetensors",
640
+ "model.vision_model.encoder.layers.26.layer_norm2.bias": "model-00001-of-00004.safetensors",
641
+ "model.vision_model.encoder.layers.26.layer_norm2.weight": "model-00001-of-00004.safetensors",
642
+ "model.vision_model.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00004.safetensors",
643
+ "model.vision_model.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00004.safetensors",
644
+ "model.vision_model.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00004.safetensors",
645
+ "model.vision_model.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00004.safetensors",
646
+ "model.vision_model.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
647
+ "model.vision_model.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
648
+ "model.vision_model.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
649
+ "model.vision_model.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
650
+ "model.vision_model.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
651
+ "model.vision_model.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
652
+ "model.vision_model.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
653
+ "model.vision_model.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
654
+ "model.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00004.safetensors",
655
+ "model.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00004.safetensors",
656
+ "model.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00004.safetensors",
657
+ "model.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00004.safetensors",
658
+ "model.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
659
+ "model.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
660
+ "model.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
661
+ "model.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
662
+ "model.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
663
+ "model.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
664
+ "model.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
665
+ "model.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
666
+ "model.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
667
+ "model.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
668
+ "model.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
669
+ "model.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
670
+ "model.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00004.safetensors",
671
+ "model.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00004.safetensors",
672
+ "model.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00004.safetensors",
673
+ "model.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00004.safetensors",
674
+ "model.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
675
+ "model.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
676
+ "model.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
677
+ "model.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
678
+ "model.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
679
+ "model.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
680
+ "model.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
681
+ "model.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
682
+ "model.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
683
+ "model.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
684
+ "model.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
685
+ "model.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
686
+ "model.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00004.safetensors",
687
+ "model.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00004.safetensors",
688
+ "model.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00004.safetensors",
689
+ "model.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00004.safetensors",
690
+ "model.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
691
+ "model.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
692
+ "model.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
693
+ "model.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
694
+ "model.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
695
+ "model.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
696
+ "model.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
697
+ "model.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
698
+ "model.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
699
+ "model.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
700
+ "model.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
701
+ "model.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
702
+ "model.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00004.safetensors",
703
+ "model.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00004.safetensors",
704
+ "model.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00004.safetensors",
705
+ "model.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00004.safetensors",
706
+ "model.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
707
+ "model.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
708
+ "model.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
709
+ "model.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
710
+ "model.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
711
+ "model.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
712
+ "model.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
713
+ "model.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
714
+ "model.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
715
+ "model.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
716
+ "model.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
717
+ "model.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
718
+ "model.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00004.safetensors",
719
+ "model.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00004.safetensors",
720
+ "model.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00004.safetensors",
721
+ "model.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00004.safetensors",
722
+ "model.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
723
+ "model.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
724
+ "model.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
725
+ "model.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
726
+ "model.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
727
+ "model.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
728
+ "model.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
729
+ "model.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
730
+ "model.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
731
+ "model.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
732
+ "model.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
733
+ "model.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
734
+ "model.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00004.safetensors",
735
+ "model.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00004.safetensors",
736
+ "model.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00004.safetensors",
737
+ "model.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00004.safetensors",
738
+ "model.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
739
+ "model.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
740
+ "model.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
741
+ "model.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
742
+ "model.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
743
+ "model.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
744
+ "model.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
745
+ "model.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
746
+ "model.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
747
+ "model.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
748
+ "model.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
749
+ "model.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
750
+ "model.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00004.safetensors",
751
+ "model.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00004.safetensors",
752
+ "model.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00004.safetensors",
753
+ "model.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00004.safetensors",
754
+ "model.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
755
+ "model.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
756
+ "model.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
757
+ "model.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
758
+ "model.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
759
+ "model.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
760
+ "model.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors",
761
+ "model.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00004.safetensors",
762
+ "model.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
763
+ "model.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
764
+ "model.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
765
+ "model.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
766
+ "model.vision_model.post_layernorm.bias": "model-00001-of-00004.safetensors",
767
+ "model.vision_model.post_layernorm.weight": "model-00001-of-00004.safetensors",
768
+ "score.bias": "model-00004-of-00004.safetensors",
769
+ "score.weight": "model-00004-of-00004.safetensors"
770
+ }
771
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_image_splitting": false,
4
+ "do_normalize": true,
5
+ "do_pad": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Idefics2ImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Idefics2Processor",
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": {
23
+ "longest_edge": 980,
24
+ "shortest_edge": 378
25
+ }
26
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "image_seq_len": 64,
3
+ "processor_class": "Idefics2Processor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<fake_token_around_image>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<image>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<end_of_utterance>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "bos_token": {
26
+ "content": "<s>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "eos_token": {
33
+ "content": "</s>",
34
+ "lstrip": false,
35
+ "normalized": false,
36
+ "rstrip": false,
37
+ "single_word": false
38
+ },
39
+ "pad_token": {
40
+ "content": "<unk>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "unk_token": {
47
+ "content": "<unk>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ }
53
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<fake_token_around_image>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<image>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<end_of_utterance>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
+ },
54
+ "additional_special_tokens": [
55
+ "<fake_token_around_image>",
56
+ "<image>",
57
+ "<end_of_utterance>"
58
+ ],
59
+ "bos_token": "<s>",
60
+ "clean_up_tokenization_spaces": false,
61
+ "do_image_splitting": false,
62
+ "eos_token": "</s>",
63
+ "legacy": false,
64
+ "model_max_length": 1000000000000000019884624838656,
65
+ "pad_token": "<unk>",
66
+ "processor_class": "Idefics2Processor",
67
+ "sp_model_kwargs": {},
68
+ "spaces_between_special_tokens": false,
69
+ "tokenizer_class": "LlamaTokenizer",
70
+ "unk_token": "<unk>",
71
+ "use_default_system_prompt": true
72
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bce3558ffbc6135d0514d61518c62f264cf594ce2cd53543394faa8cb70b079e
3
+ size 6584