Hugging Face's logo

SpaceProduct
/
videollama3-7b-bridge_rt_1-N4-140K-steps

Safetensors
dvla
custom_code
Model card Files
xet
 Community
SpaceProduct commited on
Commit
bc29c0b
·
verified ·
1 Parent(s): 84e6a53

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +27 -0
  3. chat_template.json +3 -0
  4. config.json +375 -0
  5. dataset_statistics.json +264 -0
  6. generation_config.json +7 -0
  7. merges.txt +0 -0
  8. model-00001-of-00005.safetensors +3 -0
  9. model-00002-of-00005.safetensors +3 -0
  10. model-00003-of-00005.safetensors +3 -0
  11. model-00004-of-00005.safetensors +3 -0
  12. model-00005-of-00005.safetensors +3 -0
  13. model.safetensors.index.json +786 -0
  14. preprocessor_config.json +27 -0
  15. processor_config.json +7 -0
  16. special_tokens_map.json +31 -0
  17. tokenizer.json +3 -0
  18. tokenizer_config.json +237 -0
  19. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
 
 
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
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<image>": 151665,
4
+ "<tool_call>": 151657,
5
+ "<|box_end|>": 151649,
6
+ "<|box_start|>": 151648,
7
+ "<|endoftext|>": 151643,
8
+ "<|file_sep|>": 151664,
9
+ "<|fim_middle|>": 151660,
10
+ "<|fim_pad|>": 151662,
11
+ "<|fim_prefix|>": 151659,
12
+ "<|fim_suffix|>": 151661,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|stream_end|>": 151667,
22
+ "<|stream_start|>": 151666,
23
+ "<|video_pad|>": 151656,
24
+ "<|vision_end|>": 151653,
25
+ "<|vision_pad|>": 151654,
26
+ "<|vision_start|>": 151652
27
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "\n{%- set identifier = 'im' %}\n{% for message in messages %}\n {% if add_system_prompt and loop.first and message['role'] != 'system' %}\n {{- '<|im_start|>system\nYou are VideoLLaMA3 created by Alibaba DAMO Academy, a helpful assistant to help people understand images and videos.<|im_end|>\n' -}}\n {% endif %}\n {% if message['role'] == 'stream' %}\n {% set identifier = 'stream' %}\n {% else %}\n {% set identifier = 'im' %}\n {% endif %}\n {{- '<|' + identifier + '_start|>' + message['role'] + '\n' -}}\n {% if message['content'] is string %}\n {{- message['content'] + '<|' + identifier + '_end|>\n' -}}\n {% else %}\n {% for content in message['content'] %}\n {% if content is string %}\n {{- content -}}\n {% elif content['type'] == 'text' or 'text' in content %}\n {{- content['text'] -}}\n {% elif content['type'] == 'image' or 'image' in content %}\n {% if 'timestamp' in content %}\n {{- 'Time ' + content['timestamp'] | round(1) | string + 's: ' -}}\n {% endif %}\n {{- image_token + '\n' -}}\n {% elif content['type'] == 'video' or 'video' in content %}\n {% for i in range(content['num_frames']) %}\n {% if 'timestamps' in content %}\n {{- 'Time ' + content['timestamps'][i] | round(1) | string + 's:' -}}\n {% endif %}\n {% if i < content['num_frames'] - 1 %}\n {{- image_token + ',' -}}\n {% else %}\n {{- image_token + '\n' -}}\n {% endif %}\n {% endfor %}\n {% endif %}\n {% endfor %}\n {% if identifier == 'stream' %}\n {{- '<|' + identifier + '_end|>' -}}\n {% else %}\n {{- '<|' + identifier + '_end|>\n' -}}\n {% endif %}\n {% endif %}\n{% endfor %}\n{% if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' -}}\n{% endif %}\n"
3
+ }
config.json ADDED
@@ -0,0 +1,375 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DVLAForActionPrediction"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "auto_map": {
7
+ "AutoConfig": "DAMO-NLP-SG/VideoLLaMA3-7B-Image--configuration_videollama3.Videollama3Qwen2Config",
8
+ "AutoModelForCausalLM": "DAMO-NLP-SG/VideoLLaMA3-7B-Image--modeling_videollama3.Videollama3Qwen2ForCausalLM"
9
+ },
10
+ "bos_token_id": 151643,
11
+ "eos_token_id": 151645,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 3584,
14
+ "image_token_index": 151665,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 18944,
17
+ "max_position_embeddings": 32768,
18
+ "max_window_layers": 28,
19
+ "mm_projector_type": "mlp2x_gelu",
20
+ "model_type": "dvla",
21
+ "n_action_bins": 256,
22
+ "norm_stats": {
23
+ "bridge_orig": {
24
+ "action": {
25
+ "mask": [
26
+ true,
27
+ true,
28
+ true,
29
+ true,
30
+ true,
31
+ true,
32
+ false
33
+ ],
34
+ "max": [
35
+ 0.41691166162490845,
36
+ 0.25864794850349426,
37
+ 0.21218234300613403,
38
+ 3.122201919555664,
39
+ 1.8618112802505493,
40
+ 6.272472858428955,
41
+ 1.0
42
+ ],
43
+ "mean": [
44
+ 0.00023162984871305525,
45
+ 0.00013371460954658687,
46
+ -0.00013210502220317721,
47
+ -0.00014224917686078697,
48
+ -0.0003957618318963796,
49
+ 0.00025795758119784296,
50
+ 0.5765169858932495
51
+ ],
52
+ "min": [
53
+ -0.4007510244846344,
54
+ -0.12928041815757751,
55
+ -0.22553899884223938,
56
+ -3.2010786533355713,
57
+ -1.8618112802505493,
58
+ -6.279075622558594,
59
+ 0.0
60
+ ],
61
+ "q01": [
62
+ -0.028744795620441438,
63
+ -0.041743524745106696,
64
+ -0.02612247958779335,
65
+ -0.08074554242193699,
66
+ -0.09273611158132553,
67
+ -0.20663773745298386,
68
+ 0.0
69
+ ],
70
+ "q99": [
71
+ 0.028299489319324488,
72
+ 0.04087499871850013,
73
+ 0.040158278569579056,
74
+ 0.08191050931811326,
75
+ 0.07803218640387051,
76
+ 0.2031656354665755,
77
+ 1.0
78
+ ],
79
+ "std": [
80
+ 0.009774772450327873,
81
+ 0.013701396994292736,
82
+ 0.012669386342167854,
83
+ 0.02856358513236046,
84
+ 0.03065265156328678,
85
+ 0.07559732347726822,
86
+ 0.4959997236728668
87
+ ]
88
+ },
89
+ "num_trajectories": 48624,
90
+ "num_transitions": 1728258,
91
+ "proprio": {
92
+ "max": [
93
+ 0.5735528469085693,
94
+ 0.4034728705883026,
95
+ 0.36494991183280945,
96
+ 1.3517684936523438,
97
+ 1.570796251296997,
98
+ 3.141204357147217,
99
+ 0.0,
100
+ 1.1121242046356201
101
+ ],
102
+ "mean": [
103
+ 0.30948513746261597,
104
+ 0.030666163191199303,
105
+ 0.06444736570119858,
106
+ 0.0068027242086827755,
107
+ -0.07731744647026062,
108
+ 0.10813789069652557,
109
+ 0.0,
110
+ 0.7086173892021179
111
+ ],
112
+ "min": [
113
+ -0.04167502000927925,
114
+ -0.3945816159248352,
115
+ -0.15537554025650024,
116
+ -3.141592502593994,
117
+ -1.4992541074752808,
118
+ -3.14153790473938,
119
+ 0.0,
120
+ 0.04637829214334488
121
+ ],
122
+ "q01": [
123
+ 0.17092366471886636,
124
+ -0.17033958569169044,
125
+ -0.05617850091308355,
126
+ -0.3667951425909996,
127
+ -0.5440364676713944,
128
+ -1.3451742899417878,
129
+ 0.0,
130
+ 0.052190229296684265
131
+ ],
132
+ "q99": [
133
+ 0.45397736728191357,
134
+ 0.23543687969446145,
135
+ 0.19510107412934283,
136
+ 0.3818274670839303,
137
+ 0.2794133839011189,
138
+ 1.8331137096881818,
139
+ 0.0,
140
+ 1.0105689764022827
141
+ ],
142
+ "std": [
143
+ 0.06067129969596863,
144
+ 0.09202422946691513,
145
+ 0.0516839325428009,
146
+ 0.13189035654067993,
147
+ 0.1705130785703659,
148
+ 0.5743006467819214,
149
+ 0.0,
150
+ 0.3522878885269165
151
+ ]
152
+ }
153
+ },
154
+ "fractal20220817_data": {
155
+ "action": {
156
+ "mask": [
157
+ true,
158
+ true,
159
+ true,
160
+ true,
161
+ true,
162
+ true,
163
+ false
164
+ ],
165
+ "max": [
166
+ 2.9984593391418457,
167
+ 22.09052848815918,
168
+ 2.7507524490356445,
169
+ 1.570636510848999,
170
+ 1.5321086645126343,
171
+ 1.5691522359848022,
172
+ 1.0
173
+ ],
174
+ "mean": [
175
+ 0.0070160930044949055,
176
+ 0.006287453696131706,
177
+ -0.012577778659760952,
178
+ 0.04329700767993927,
179
+ -0.005719248205423355,
180
+ 0.0009455775725655258,
181
+ 0.535513699054718
182
+ ],
183
+ "min": [
184
+ -2.0204520225524902,
185
+ -5.497899532318115,
186
+ -2.031663417816162,
187
+ -1.569917917251587,
188
+ -1.569892168045044,
189
+ -1.570419430732727,
190
+ 0.0
191
+ ],
192
+ "q01": [
193
+ -0.22409614741802214,
194
+ -0.14817706286907195,
195
+ -0.2316769856214523,
196
+ -0.3531744807958603,
197
+ -0.4192173588275909,
198
+ -0.4368023717403412,
199
+ 0.0
200
+ ],
201
+ "q99": [
202
+ 0.17836674451827994,
203
+ 0.14942033141851413,
204
+ 0.21879618436098075,
205
+ 0.5897578334808342,
206
+ 0.35292886614799457,
207
+ 0.4487913608551022,
208
+ 1.0
209
+ ],
210
+ "std": [
211
+ 0.0693204402923584,
212
+ 0.060718413442373276,
213
+ 0.07362836599349976,
214
+ 0.15637660026550293,
215
+ 0.13175784051418304,
216
+ 0.146182581782341,
217
+ 0.4972381293773651
218
+ ]
219
+ },
220
+ "num_trajectories": 78480,
221
+ "num_transitions": 3404867,
222
+ "proprio": {
223
+ "max": [
224
+ 1.0534898042678833,
225
+ 0.48018959164619446,
226
+ 1.6896663904190063,
227
+ 0.9999993443489075,
228
+ 0.9999874830245972,
229
+ 0.9554369449615479,
230
+ 0.9914546012878418,
231
+ 1.0
232
+ ],
233
+ "mean": [
234
+ 0.5597754120826721,
235
+ -0.0832320973277092,
236
+ 0.7760888934135437,
237
+ -0.24704332649707794,
238
+ 0.49434685707092285,
239
+ 0.09261937439441681,
240
+ 0.20921756327152252,
241
+ 0.42606088519096375
242
+ ],
243
+ "min": [
244
+ -0.4436439275741577,
245
+ -0.9970501065254211,
246
+ -0.006579156965017319,
247
+ -0.8643477559089661,
248
+ -0.7079970240592957,
249
+ -0.7688722014427185,
250
+ -0.4999994933605194,
251
+ 0.0
252
+ ],
253
+ "q01": [
254
+ 0.32485780119895935,
255
+ -0.2830313414335251,
256
+ 0.14108185589313507,
257
+ -0.6863587307929992,
258
+ -0.6807721078395843,
259
+ -0.36089446604251857,
260
+ -0.4545843780040741,
261
+ 0.0
262
+ ],
263
+ "q99": [
264
+ 0.8753369486331939,
265
+ 0.21245125174522383,
266
+ 1.072377111911773,
267
+ 0.9382593035697933,
268
+ 0.9568788063526152,
269
+ 0.4598054605722425,
270
+ 0.7213053238391873,
271
+ 1.0
272
+ ],
273
+ "std": [
274
+ 0.12438706308603287,
275
+ 0.1155894473195076,
276
+ 0.24558264017105103,
277
+ 0.5133047699928284,
278
+ 0.522326648235321,
279
+ 0.16654427349567413,
280
+ 0.27579590678215027,
281
+ 0.4560266435146332
282
+ ]
283
+ }
284
+ }
285
+ },
286
+ "num_attention_heads": 28,
287
+ "num_hidden_layers": 28,
288
+ "num_key_value_heads": 4,
289
+ "pad_to_multiple_of": 8,
290
+ "rms_norm_eps": 1e-06,
291
+ "rope_scaling": null,
292
+ "rope_theta": 1000000.0,
293
+ "sliding_window": null,
294
+ "tie_word_embeddings": false,
295
+ "torch_dtype": "float16",
296
+ "transformers_version": "4.50.3",
297
+ "use_cache": false,
298
+ "use_sliding_window": false,
299
+ "use_token_compression": false,
300
+ "vision_encoder": "videollamae3vision_encoder",
301
+ "vision_encoder_config": {
302
+ "_attn_implementation_autoset": false,
303
+ "_name_or_path": "",
304
+ "add_cross_attention": false,
305
+ "architectures": null,
306
+ "attention_dropout": 0.0,
307
+ "bad_words_ids": null,
308
+ "begin_suppress_tokens": null,
309
+ "bos_token_id": null,
310
+ "chunk_size_feed_forward": 0,
311
+ "cross_attention_hidden_size": null,
312
+ "decoder_start_token_id": null,
313
+ "diversity_penalty": 0.0,
314
+ "do_sample": false,
315
+ "early_stopping": false,
316
+ "encoder_no_repeat_ngram_size": 0,
317
+ "eos_token_id": null,
318
+ "exponential_decay_length_penalty": null,
319
+ "finetuning_task": null,
320
+ "forced_bos_token_id": null,
321
+ "forced_eos_token_id": null,
322
+ "hidden_act": "gelu_pytorch_tanh",
323
+ "hidden_size": 1152,
324
+ "id2label": {
325
+ "0": "LABEL_0",
326
+ "1": "LABEL_1"
327
+ },
328
+ "intermediate_size": 4304,
329
+ "is_decoder": false,
330
+ "is_encoder_decoder": false,
331
+ "label2id": {
332
+ "LABEL_0": 0,
333
+ "LABEL_1": 1
334
+ },
335
+ "layer_norm_eps": 1e-06,
336
+ "length_penalty": 1.0,
337
+ "max_length": 20,
338
+ "min_length": 0,
339
+ "model_type": "videollama3_vision_encoder",
340
+ "no_repeat_ngram_size": 0,
341
+ "num_attention_heads": 16,
342
+ "num_beam_groups": 1,
343
+ "num_beams": 1,
344
+ "num_channels": 3,
345
+ "num_hidden_layers": 27,
346
+ "num_return_sequences": 1,
347
+ "output_attentions": false,
348
+ "output_hidden_states": false,
349
+ "output_scores": false,
350
+ "pad_token_id": null,
351
+ "patch_size": 14,
352
+ "prefix": null,
353
+ "problem_type": null,
354
+ "pruned_heads": {},
355
+ "remove_invalid_values": false,
356
+ "repetition_penalty": 1.0,
357
+ "return_dict": true,
358
+ "return_dict_in_generate": false,
359
+ "sep_token_id": null,
360
+ "suppress_tokens": null,
361
+ "task_specific_params": null,
362
+ "temperature": 1.0,
363
+ "tf_legacy_loss": false,
364
+ "tie_encoder_decoder": false,
365
+ "tie_word_embeddings": true,
366
+ "tokenizer_class": null,
367
+ "top_k": 50,
368
+ "top_p": 1.0,
369
+ "torch_dtype": null,
370
+ "torchscript": false,
371
+ "typical_p": 1.0,
372
+ "use_bfloat16": false
373
+ },
374
+ "vocab_size": 152064
375
+ }
dataset_statistics.json ADDED
@@ -0,0 +1,264 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bridge_orig": {
3
+ "action": {
4
+ "mean": [
5
+ 0.00023162984871305525,
6
+ 0.00013371460954658687,
7
+ -0.00013210502220317721,
8
+ -0.00014224917686078697,
9
+ -0.0003957618318963796,
10
+ 0.00025795758119784296,
11
+ 0.5765169858932495
12
+ ],
13
+ "std": [
14
+ 0.009774772450327873,
15
+ 0.013701396994292736,
16
+ 0.012669386342167854,
17
+ 0.02856358513236046,
18
+ 0.03065265156328678,
19
+ 0.07559732347726822,
20
+ 0.4959997236728668
21
+ ],
22
+ "max": [
23
+ 0.41691166162490845,
24
+ 0.25864794850349426,
25
+ 0.21218234300613403,
26
+ 3.122201919555664,
27
+ 1.8618112802505493,
28
+ 6.272472858428955,
29
+ 1.0
30
+ ],
31
+ "min": [
32
+ -0.4007510244846344,
33
+ -0.12928041815757751,
34
+ -0.22553899884223938,
35
+ -3.2010786533355713,
36
+ -1.8618112802505493,
37
+ -6.279075622558594,
38
+ 0.0
39
+ ],
40
+ "q01": [
41
+ -0.028744795620441438,
42
+ -0.041743524745106696,
43
+ -0.02612247958779335,
44
+ -0.08074554242193699,
45
+ -0.09273611158132553,
46
+ -0.20663773745298386,
47
+ 0.0
48
+ ],
49
+ "q99": [
50
+ 0.028299489319324488,
51
+ 0.04087499871850013,
52
+ 0.040158278569579056,
53
+ 0.08191050931811326,
54
+ 0.07803218640387051,
55
+ 0.2031656354665755,
56
+ 1.0
57
+ ],
58
+ "mask": [
59
+ true,
60
+ true,
61
+ true,
62
+ true,
63
+ true,
64
+ true,
65
+ false
66
+ ]
67
+ },
68
+ "proprio": {
69
+ "mean": [
70
+ 0.30948513746261597,
71
+ 0.030666163191199303,
72
+ 0.06444736570119858,
73
+ 0.0068027242086827755,
74
+ -0.07731744647026062,
75
+ 0.10813789069652557,
76
+ 0.0,
77
+ 0.7086173892021179
78
+ ],
79
+ "std": [
80
+ 0.06067129969596863,
81
+ 0.09202422946691513,
82
+ 0.0516839325428009,
83
+ 0.13189035654067993,
84
+ 0.1705130785703659,
85
+ 0.5743006467819214,
86
+ 0.0,
87
+ 0.3522878885269165
88
+ ],
89
+ "max": [
90
+ 0.5735528469085693,
91
+ 0.4034728705883026,
92
+ 0.36494991183280945,
93
+ 1.3517684936523438,
94
+ 1.570796251296997,
95
+ 3.141204357147217,
96
+ 0.0,
97
+ 1.1121242046356201
98
+ ],
99
+ "min": [
100
+ -0.04167502000927925,
101
+ -0.3945816159248352,
102
+ -0.15537554025650024,
103
+ -3.141592502593994,
104
+ -1.4992541074752808,
105
+ -3.14153790473938,
106
+ 0.0,
107
+ 0.04637829214334488
108
+ ],
109
+ "q01": [
110
+ 0.17092366471886636,
111
+ -0.17033958569169044,
112
+ -0.05617850091308355,
113
+ -0.3667951425909996,
114
+ -0.5440364676713944,
115
+ -1.3451742899417878,
116
+ 0.0,
117
+ 0.052190229296684265
118
+ ],
119
+ "q99": [
120
+ 0.45397736728191357,
121
+ 0.23543687969446145,
122
+ 0.19510107412934283,
123
+ 0.3818274670839303,
124
+ 0.2794133839011189,
125
+ 1.8331137096881818,
126
+ 0.0,
127
+ 1.0105689764022827
128
+ ]
129
+ },
130
+ "num_transitions": 1728258,
131
+ "num_trajectories": 48624
132
+ },
133
+ "fractal20220817_data": {
134
+ "action": {
135
+ "mean": [
136
+ 0.0070160930044949055,
137
+ 0.006287453696131706,
138
+ -0.012577778659760952,
139
+ 0.04329700767993927,
140
+ -0.005719248205423355,
141
+ 0.0009455775725655258,
142
+ 0.535513699054718
143
+ ],
144
+ "std": [
145
+ 0.0693204402923584,
146
+ 0.060718413442373276,
147
+ 0.07362836599349976,
148
+ 0.15637660026550293,
149
+ 0.13175784051418304,
150
+ 0.146182581782341,
151
+ 0.4972381293773651
152
+ ],
153
+ "max": [
154
+ 2.9984593391418457,
155
+ 22.09052848815918,
156
+ 2.7507524490356445,
157
+ 1.570636510848999,
158
+ 1.5321086645126343,
159
+ 1.5691522359848022,
160
+ 1.0
161
+ ],
162
+ "min": [
163
+ -2.0204520225524902,
164
+ -5.497899532318115,
165
+ -2.031663417816162,
166
+ -1.569917917251587,
167
+ -1.569892168045044,
168
+ -1.570419430732727,
169
+ 0.0
170
+ ],
171
+ "q01": [
172
+ -0.22409614741802214,
173
+ -0.14817706286907195,
174
+ -0.2316769856214523,
175
+ -0.3531744807958603,
176
+ -0.4192173588275909,
177
+ -0.4368023717403412,
178
+ 0.0
179
+ ],
180
+ "q99": [
181
+ 0.17836674451827994,
182
+ 0.14942033141851413,
183
+ 0.21879618436098075,
184
+ 0.5897578334808342,
185
+ 0.35292886614799457,
186
+ 0.4487913608551022,
187
+ 1.0
188
+ ],
189
+ "mask": [
190
+ true,
191
+ true,
192
+ true,
193
+ true,
194
+ true,
195
+ true,
196
+ false
197
+ ]
198
+ },
199
+ "proprio": {
200
+ "mean": [
201
+ 0.5597754120826721,
202
+ -0.0832320973277092,
203
+ 0.7760888934135437,
204
+ -0.24704332649707794,
205
+ 0.49434685707092285,
206
+ 0.09261937439441681,
207
+ 0.20921756327152252,
208
+ 0.42606088519096375
209
+ ],
210
+ "std": [
211
+ 0.12438706308603287,
212
+ 0.1155894473195076,
213
+ 0.24558264017105103,
214
+ 0.5133047699928284,
215
+ 0.522326648235321,
216
+ 0.16654427349567413,
217
+ 0.27579590678215027,
218
+ 0.4560266435146332
219
+ ],
220
+ "max": [
221
+ 1.0534898042678833,
222
+ 0.48018959164619446,
223
+ 1.6896663904190063,
224
+ 0.9999993443489075,
225
+ 0.9999874830245972,
226
+ 0.9554369449615479,
227
+ 0.9914546012878418,
228
+ 1.0
229
+ ],
230
+ "min": [
231
+ -0.4436439275741577,
232
+ -0.9970501065254211,
233
+ -0.006579156965017319,
234
+ -0.8643477559089661,
235
+ -0.7079970240592957,
236
+ -0.7688722014427185,
237
+ -0.4999994933605194,
238
+ 0.0
239
+ ],
240
+ "q01": [
241
+ 0.32485780119895935,
242
+ -0.2830313414335251,
243
+ 0.14108185589313507,
244
+ -0.6863587307929992,
245
+ -0.6807721078395843,
246
+ -0.36089446604251857,
247
+ -0.4545843780040741,
248
+ 0.0
249
+ ],
250
+ "q99": [
251
+ 0.8753369486331939,
252
+ 0.21245125174522383,
253
+ 1.072377111911773,
254
+ 0.9382593035697933,
255
+ 0.9568788063526152,
256
+ 0.4598054605722425,
257
+ 0.7213053238391873,
258
+ 1.0
259
+ ]
260
+ },
261
+ "num_transitions": 3404867,
262
+ "num_trajectories": 78480
263
+ }
264
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.50.3",
6
+ "use_cache": false
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b1cc3cbc2b93c20e37b9d44dc6e286b80c5cabdf911cb76adf6d36a22c08ea6
3
+ size 3945426792
model-00002-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d7f971381224e848a073e3ae1cc5c9dee039f3c86df45675725a69d3dd76012
3
+ size 3864726256
model-00003-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:295fabe51c41312b5381292b7780254e38fbdf35d35ea3a16eafbe0ba203d742
3
+ size 3864726312
model-00004-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27a53e0e5f95ed3f959b65358e59c51f45e13cec4d842c1ed1ce8d199944d44e
3
+ size 3324711680
model-00005-of-00005.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:131ff20de25975518160e589ae401e966d381997f2caa53130c0cc45370369eb
3
+ size 1089994880
model.safetensors.index.json ADDED
@@ -0,0 +1,786 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16089489888
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00005-of-00005.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00005.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00005.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00005.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
260
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
261
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
262
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
263
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
264
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
265
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
266
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
267
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
268
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
269
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
270
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
271
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
272
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
273
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
274
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
275
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
276
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
277
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
278
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
279
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
280
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
281
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
282
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
283
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
284
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
285
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
286
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
287
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
288
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
289
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
290
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
291
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
292
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
293
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
294
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
295
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
296
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
297
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
298
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
299
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
300
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
301
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",
302
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
303
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
304
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
305
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
306
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
307
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
308
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
309
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
310
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
311
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
312
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
313
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
314
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
315
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
316
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
317
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
318
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
319
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
320
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
321
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
322
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
323
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
324
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
325
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
326
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
327
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
328
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
329
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
330
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
331
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
332
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
333
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
334
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
335
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
336
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
337
+ "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",
338
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
339
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
340
+ "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",
341
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
342
+ "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",
343
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
344
+ "model.mm_projector.readout.0.bias": "model-00004-of-00005.safetensors",
345
+ "model.mm_projector.readout.0.weight": "model-00004-of-00005.safetensors",
346
+ "model.mm_projector.readout.2.bias": "model-00004-of-00005.safetensors",
347
+ "model.mm_projector.readout.2.weight": "model-00004-of-00005.safetensors",
348
+ "model.norm.weight": "model-00004-of-00005.safetensors",
349
+ "model.vision_encoder.embeddings.patch_embedding.bias": "model-00004-of-00005.safetensors",
350
+ "model.vision_encoder.embeddings.patch_embedding.weight": "model-00004-of-00005.safetensors",
351
+ "model.vision_encoder.encoder.layers.0.layer_norm1.bias": "model-00004-of-00005.safetensors",
352
+ "model.vision_encoder.encoder.layers.0.layer_norm1.weight": "model-00004-of-00005.safetensors",
353
+ "model.vision_encoder.encoder.layers.0.layer_norm2.bias": "model-00004-of-00005.safetensors",
354
+ "model.vision_encoder.encoder.layers.0.layer_norm2.weight": "model-00004-of-00005.safetensors",
355
+ "model.vision_encoder.encoder.layers.0.mlp.fc1.bias": "model-00004-of-00005.safetensors",
356
+ "model.vision_encoder.encoder.layers.0.mlp.fc1.weight": "model-00004-of-00005.safetensors",
357
+ "model.vision_encoder.encoder.layers.0.mlp.fc2.bias": "model-00004-of-00005.safetensors",
358
+ "model.vision_encoder.encoder.layers.0.mlp.fc2.weight": "model-00004-of-00005.safetensors",
359
+ "model.vision_encoder.encoder.layers.0.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
360
+ "model.vision_encoder.encoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
361
+ "model.vision_encoder.encoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
362
+ "model.vision_encoder.encoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
363
+ "model.vision_encoder.encoder.layers.0.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
364
+ "model.vision_encoder.encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
365
+ "model.vision_encoder.encoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
366
+ "model.vision_encoder.encoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
367
+ "model.vision_encoder.encoder.layers.1.layer_norm1.bias": "model-00004-of-00005.safetensors",
368
+ "model.vision_encoder.encoder.layers.1.layer_norm1.weight": "model-00004-of-00005.safetensors",
369
+ "model.vision_encoder.encoder.layers.1.layer_norm2.bias": "model-00004-of-00005.safetensors",
370
+ "model.vision_encoder.encoder.layers.1.layer_norm2.weight": "model-00004-of-00005.safetensors",
371
+ "model.vision_encoder.encoder.layers.1.mlp.fc1.bias": "model-00004-of-00005.safetensors",
372
+ "model.vision_encoder.encoder.layers.1.mlp.fc1.weight": "model-00004-of-00005.safetensors",
373
+ "model.vision_encoder.encoder.layers.1.mlp.fc2.bias": "model-00004-of-00005.safetensors",
374
+ "model.vision_encoder.encoder.layers.1.mlp.fc2.weight": "model-00004-of-00005.safetensors",
375
+ "model.vision_encoder.encoder.layers.1.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
376
+ "model.vision_encoder.encoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
377
+ "model.vision_encoder.encoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
378
+ "model.vision_encoder.encoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
379
+ "model.vision_encoder.encoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
380
+ "model.vision_encoder.encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
381
+ "model.vision_encoder.encoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
382
+ "model.vision_encoder.encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
383
+ "model.vision_encoder.encoder.layers.10.layer_norm1.bias": "model-00004-of-00005.safetensors",
384
+ "model.vision_encoder.encoder.layers.10.layer_norm1.weight": "model-00004-of-00005.safetensors",
385
+ "model.vision_encoder.encoder.layers.10.layer_norm2.bias": "model-00004-of-00005.safetensors",
386
+ "model.vision_encoder.encoder.layers.10.layer_norm2.weight": "model-00004-of-00005.safetensors",
387
+ "model.vision_encoder.encoder.layers.10.mlp.fc1.bias": "model-00004-of-00005.safetensors",
388
+ "model.vision_encoder.encoder.layers.10.mlp.fc1.weight": "model-00004-of-00005.safetensors",
389
+ "model.vision_encoder.encoder.layers.10.mlp.fc2.bias": "model-00004-of-00005.safetensors",
390
+ "model.vision_encoder.encoder.layers.10.mlp.fc2.weight": "model-00004-of-00005.safetensors",
391
+ "model.vision_encoder.encoder.layers.10.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
392
+ "model.vision_encoder.encoder.layers.10.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
393
+ "model.vision_encoder.encoder.layers.10.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
394
+ "model.vision_encoder.encoder.layers.10.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
395
+ "model.vision_encoder.encoder.layers.10.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
396
+ "model.vision_encoder.encoder.layers.10.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
397
+ "model.vision_encoder.encoder.layers.10.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
398
+ "model.vision_encoder.encoder.layers.10.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
399
+ "model.vision_encoder.encoder.layers.11.layer_norm1.bias": "model-00004-of-00005.safetensors",
400
+ "model.vision_encoder.encoder.layers.11.layer_norm1.weight": "model-00004-of-00005.safetensors",
401
+ "model.vision_encoder.encoder.layers.11.layer_norm2.bias": "model-00004-of-00005.safetensors",
402
+ "model.vision_encoder.encoder.layers.11.layer_norm2.weight": "model-00004-of-00005.safetensors",
403
+ "model.vision_encoder.encoder.layers.11.mlp.fc1.bias": "model-00004-of-00005.safetensors",
404
+ "model.vision_encoder.encoder.layers.11.mlp.fc1.weight": "model-00004-of-00005.safetensors",
405
+ "model.vision_encoder.encoder.layers.11.mlp.fc2.bias": "model-00004-of-00005.safetensors",
406
+ "model.vision_encoder.encoder.layers.11.mlp.fc2.weight": "model-00004-of-00005.safetensors",
407
+ "model.vision_encoder.encoder.layers.11.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
408
+ "model.vision_encoder.encoder.layers.11.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
409
+ "model.vision_encoder.encoder.layers.11.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
410
+ "model.vision_encoder.encoder.layers.11.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
411
+ "model.vision_encoder.encoder.layers.11.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
412
+ "model.vision_encoder.encoder.layers.11.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
413
+ "model.vision_encoder.encoder.layers.11.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
414
+ "model.vision_encoder.encoder.layers.11.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
415
+ "model.vision_encoder.encoder.layers.12.layer_norm1.bias": "model-00004-of-00005.safetensors",
416
+ "model.vision_encoder.encoder.layers.12.layer_norm1.weight": "model-00004-of-00005.safetensors",
417
+ "model.vision_encoder.encoder.layers.12.layer_norm2.bias": "model-00004-of-00005.safetensors",
418
+ "model.vision_encoder.encoder.layers.12.layer_norm2.weight": "model-00004-of-00005.safetensors",
419
+ "model.vision_encoder.encoder.layers.12.mlp.fc1.bias": "model-00004-of-00005.safetensors",
420
+ "model.vision_encoder.encoder.layers.12.mlp.fc1.weight": "model-00004-of-00005.safetensors",
421
+ "model.vision_encoder.encoder.layers.12.mlp.fc2.bias": "model-00004-of-00005.safetensors",
422
+ "model.vision_encoder.encoder.layers.12.mlp.fc2.weight": "model-00004-of-00005.safetensors",
423
+ "model.vision_encoder.encoder.layers.12.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
424
+ "model.vision_encoder.encoder.layers.12.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
425
+ "model.vision_encoder.encoder.layers.12.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
426
+ "model.vision_encoder.encoder.layers.12.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
427
+ "model.vision_encoder.encoder.layers.12.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
428
+ "model.vision_encoder.encoder.layers.12.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
429
+ "model.vision_encoder.encoder.layers.12.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
430
+ "model.vision_encoder.encoder.layers.12.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
431
+ "model.vision_encoder.encoder.layers.13.layer_norm1.bias": "model-00004-of-00005.safetensors",
432
+ "model.vision_encoder.encoder.layers.13.layer_norm1.weight": "model-00004-of-00005.safetensors",
433
+ "model.vision_encoder.encoder.layers.13.layer_norm2.bias": "model-00004-of-00005.safetensors",
434
+ "model.vision_encoder.encoder.layers.13.layer_norm2.weight": "model-00004-of-00005.safetensors",
435
+ "model.vision_encoder.encoder.layers.13.mlp.fc1.bias": "model-00004-of-00005.safetensors",
436
+ "model.vision_encoder.encoder.layers.13.mlp.fc1.weight": "model-00004-of-00005.safetensors",
437
+ "model.vision_encoder.encoder.layers.13.mlp.fc2.bias": "model-00004-of-00005.safetensors",
438
+ "model.vision_encoder.encoder.layers.13.mlp.fc2.weight": "model-00004-of-00005.safetensors",
439
+ "model.vision_encoder.encoder.layers.13.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
440
+ "model.vision_encoder.encoder.layers.13.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
441
+ "model.vision_encoder.encoder.layers.13.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
442
+ "model.vision_encoder.encoder.layers.13.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
443
+ "model.vision_encoder.encoder.layers.13.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
444
+ "model.vision_encoder.encoder.layers.13.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
445
+ "model.vision_encoder.encoder.layers.13.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
446
+ "model.vision_encoder.encoder.layers.13.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
447
+ "model.vision_encoder.encoder.layers.14.layer_norm1.bias": "model-00004-of-00005.safetensors",
448
+ "model.vision_encoder.encoder.layers.14.layer_norm1.weight": "model-00004-of-00005.safetensors",
449
+ "model.vision_encoder.encoder.layers.14.layer_norm2.bias": "model-00004-of-00005.safetensors",
450
+ "model.vision_encoder.encoder.layers.14.layer_norm2.weight": "model-00004-of-00005.safetensors",
451
+ "model.vision_encoder.encoder.layers.14.mlp.fc1.bias": "model-00004-of-00005.safetensors",
452
+ "model.vision_encoder.encoder.layers.14.mlp.fc1.weight": "model-00004-of-00005.safetensors",
453
+ "model.vision_encoder.encoder.layers.14.mlp.fc2.bias": "model-00004-of-00005.safetensors",
454
+ "model.vision_encoder.encoder.layers.14.mlp.fc2.weight": "model-00004-of-00005.safetensors",
455
+ "model.vision_encoder.encoder.layers.14.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
456
+ "model.vision_encoder.encoder.layers.14.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
457
+ "model.vision_encoder.encoder.layers.14.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
458
+ "model.vision_encoder.encoder.layers.14.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
459
+ "model.vision_encoder.encoder.layers.14.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
460
+ "model.vision_encoder.encoder.layers.14.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
461
+ "model.vision_encoder.encoder.layers.14.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
462
+ "model.vision_encoder.encoder.layers.14.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
463
+ "model.vision_encoder.encoder.layers.15.layer_norm1.bias": "model-00004-of-00005.safetensors",
464
+ "model.vision_encoder.encoder.layers.15.layer_norm1.weight": "model-00004-of-00005.safetensors",
465
+ "model.vision_encoder.encoder.layers.15.layer_norm2.bias": "model-00004-of-00005.safetensors",
466
+ "model.vision_encoder.encoder.layers.15.layer_norm2.weight": "model-00004-of-00005.safetensors",
467
+ "model.vision_encoder.encoder.layers.15.mlp.fc1.bias": "model-00004-of-00005.safetensors",
468
+ "model.vision_encoder.encoder.layers.15.mlp.fc1.weight": "model-00004-of-00005.safetensors",
469
+ "model.vision_encoder.encoder.layers.15.mlp.fc2.bias": "model-00004-of-00005.safetensors",
470
+ "model.vision_encoder.encoder.layers.15.mlp.fc2.weight": "model-00004-of-00005.safetensors",
471
+ "model.vision_encoder.encoder.layers.15.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
472
+ "model.vision_encoder.encoder.layers.15.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
473
+ "model.vision_encoder.encoder.layers.15.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
474
+ "model.vision_encoder.encoder.layers.15.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
475
+ "model.vision_encoder.encoder.layers.15.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
476
+ "model.vision_encoder.encoder.layers.15.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
477
+ "model.vision_encoder.encoder.layers.15.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
478
+ "model.vision_encoder.encoder.layers.15.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
479
+ "model.vision_encoder.encoder.layers.16.layer_norm1.bias": "model-00004-of-00005.safetensors",
480
+ "model.vision_encoder.encoder.layers.16.layer_norm1.weight": "model-00004-of-00005.safetensors",
481
+ "model.vision_encoder.encoder.layers.16.layer_norm2.bias": "model-00004-of-00005.safetensors",
482
+ "model.vision_encoder.encoder.layers.16.layer_norm2.weight": "model-00004-of-00005.safetensors",
483
+ "model.vision_encoder.encoder.layers.16.mlp.fc1.bias": "model-00004-of-00005.safetensors",
484
+ "model.vision_encoder.encoder.layers.16.mlp.fc1.weight": "model-00004-of-00005.safetensors",
485
+ "model.vision_encoder.encoder.layers.16.mlp.fc2.bias": "model-00004-of-00005.safetensors",
486
+ "model.vision_encoder.encoder.layers.16.mlp.fc2.weight": "model-00004-of-00005.safetensors",
487
+ "model.vision_encoder.encoder.layers.16.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
488
+ "model.vision_encoder.encoder.layers.16.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
489
+ "model.vision_encoder.encoder.layers.16.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
490
+ "model.vision_encoder.encoder.layers.16.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
491
+ "model.vision_encoder.encoder.layers.16.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
492
+ "model.vision_encoder.encoder.layers.16.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
493
+ "model.vision_encoder.encoder.layers.16.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
494
+ "model.vision_encoder.encoder.layers.16.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
495
+ "model.vision_encoder.encoder.layers.17.layer_norm1.bias": "model-00004-of-00005.safetensors",
496
+ "model.vision_encoder.encoder.layers.17.layer_norm1.weight": "model-00004-of-00005.safetensors",
497
+ "model.vision_encoder.encoder.layers.17.layer_norm2.bias": "model-00004-of-00005.safetensors",
498
+ "model.vision_encoder.encoder.layers.17.layer_norm2.weight": "model-00004-of-00005.safetensors",
499
+ "model.vision_encoder.encoder.layers.17.mlp.fc1.bias": "model-00004-of-00005.safetensors",
500
+ "model.vision_encoder.encoder.layers.17.mlp.fc1.weight": "model-00004-of-00005.safetensors",
501
+ "model.vision_encoder.encoder.layers.17.mlp.fc2.bias": "model-00004-of-00005.safetensors",
502
+ "model.vision_encoder.encoder.layers.17.mlp.fc2.weight": "model-00004-of-00005.safetensors",
503
+ "model.vision_encoder.encoder.layers.17.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
504
+ "model.vision_encoder.encoder.layers.17.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
505
+ "model.vision_encoder.encoder.layers.17.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
506
+ "model.vision_encoder.encoder.layers.17.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
507
+ "model.vision_encoder.encoder.layers.17.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
508
+ "model.vision_encoder.encoder.layers.17.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
509
+ "model.vision_encoder.encoder.layers.17.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
510
+ "model.vision_encoder.encoder.layers.17.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
511
+ "model.vision_encoder.encoder.layers.18.layer_norm1.bias": "model-00004-of-00005.safetensors",
512
+ "model.vision_encoder.encoder.layers.18.layer_norm1.weight": "model-00004-of-00005.safetensors",
513
+ "model.vision_encoder.encoder.layers.18.layer_norm2.bias": "model-00004-of-00005.safetensors",
514
+ "model.vision_encoder.encoder.layers.18.layer_norm2.weight": "model-00004-of-00005.safetensors",
515
+ "model.vision_encoder.encoder.layers.18.mlp.fc1.bias": "model-00004-of-00005.safetensors",
516
+ "model.vision_encoder.encoder.layers.18.mlp.fc1.weight": "model-00004-of-00005.safetensors",
517
+ "model.vision_encoder.encoder.layers.18.mlp.fc2.bias": "model-00004-of-00005.safetensors",
518
+ "model.vision_encoder.encoder.layers.18.mlp.fc2.weight": "model-00004-of-00005.safetensors",
519
+ "model.vision_encoder.encoder.layers.18.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
520
+ "model.vision_encoder.encoder.layers.18.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
521
+ "model.vision_encoder.encoder.layers.18.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
522
+ "model.vision_encoder.encoder.layers.18.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
523
+ "model.vision_encoder.encoder.layers.18.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
524
+ "model.vision_encoder.encoder.layers.18.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
525
+ "model.vision_encoder.encoder.layers.18.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
526
+ "model.vision_encoder.encoder.layers.18.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
527
+ "model.vision_encoder.encoder.layers.19.layer_norm1.bias": "model-00004-of-00005.safetensors",
528
+ "model.vision_encoder.encoder.layers.19.layer_norm1.weight": "model-00004-of-00005.safetensors",
529
+ "model.vision_encoder.encoder.layers.19.layer_norm2.bias": "model-00004-of-00005.safetensors",
530
+ "model.vision_encoder.encoder.layers.19.layer_norm2.weight": "model-00004-of-00005.safetensors",
531
+ "model.vision_encoder.encoder.layers.19.mlp.fc1.bias": "model-00004-of-00005.safetensors",
532
+ "model.vision_encoder.encoder.layers.19.mlp.fc1.weight": "model-00004-of-00005.safetensors",
533
+ "model.vision_encoder.encoder.layers.19.mlp.fc2.bias": "model-00004-of-00005.safetensors",
534
+ "model.vision_encoder.encoder.layers.19.mlp.fc2.weight": "model-00004-of-00005.safetensors",
535
+ "model.vision_encoder.encoder.layers.19.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
536
+ "model.vision_encoder.encoder.layers.19.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
537
+ "model.vision_encoder.encoder.layers.19.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
538
+ "model.vision_encoder.encoder.layers.19.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
539
+ "model.vision_encoder.encoder.layers.19.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
540
+ "model.vision_encoder.encoder.layers.19.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
541
+ "model.vision_encoder.encoder.layers.19.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
542
+ "model.vision_encoder.encoder.layers.19.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
543
+ "model.vision_encoder.encoder.layers.2.layer_norm1.bias": "model-00004-of-00005.safetensors",
544
+ "model.vision_encoder.encoder.layers.2.layer_norm1.weight": "model-00004-of-00005.safetensors",
545
+ "model.vision_encoder.encoder.layers.2.layer_norm2.bias": "model-00004-of-00005.safetensors",
546
+ "model.vision_encoder.encoder.layers.2.layer_norm2.weight": "model-00004-of-00005.safetensors",
547
+ "model.vision_encoder.encoder.layers.2.mlp.fc1.bias": "model-00004-of-00005.safetensors",
548
+ "model.vision_encoder.encoder.layers.2.mlp.fc1.weight": "model-00004-of-00005.safetensors",
549
+ "model.vision_encoder.encoder.layers.2.mlp.fc2.bias": "model-00004-of-00005.safetensors",
550
+ "model.vision_encoder.encoder.layers.2.mlp.fc2.weight": "model-00004-of-00005.safetensors",
551
+ "model.vision_encoder.encoder.layers.2.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
552
+ "model.vision_encoder.encoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
553
+ "model.vision_encoder.encoder.layers.2.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
554
+ "model.vision_encoder.encoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
555
+ "model.vision_encoder.encoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
556
+ "model.vision_encoder.encoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
557
+ "model.vision_encoder.encoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
558
+ "model.vision_encoder.encoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
559
+ "model.vision_encoder.encoder.layers.20.layer_norm1.bias": "model-00004-of-00005.safetensors",
560
+ "model.vision_encoder.encoder.layers.20.layer_norm1.weight": "model-00004-of-00005.safetensors",
561
+ "model.vision_encoder.encoder.layers.20.layer_norm2.bias": "model-00004-of-00005.safetensors",
562
+ "model.vision_encoder.encoder.layers.20.layer_norm2.weight": "model-00004-of-00005.safetensors",
563
+ "model.vision_encoder.encoder.layers.20.mlp.fc1.bias": "model-00004-of-00005.safetensors",
564
+ "model.vision_encoder.encoder.layers.20.mlp.fc1.weight": "model-00004-of-00005.safetensors",
565
+ "model.vision_encoder.encoder.layers.20.mlp.fc2.bias": "model-00004-of-00005.safetensors",
566
+ "model.vision_encoder.encoder.layers.20.mlp.fc2.weight": "model-00004-of-00005.safetensors",
567
+ "model.vision_encoder.encoder.layers.20.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
568
+ "model.vision_encoder.encoder.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
569
+ "model.vision_encoder.encoder.layers.20.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
570
+ "model.vision_encoder.encoder.layers.20.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
571
+ "model.vision_encoder.encoder.layers.20.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
572
+ "model.vision_encoder.encoder.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
573
+ "model.vision_encoder.encoder.layers.20.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
574
+ "model.vision_encoder.encoder.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
575
+ "model.vision_encoder.encoder.layers.21.layer_norm1.bias": "model-00004-of-00005.safetensors",
576
+ "model.vision_encoder.encoder.layers.21.layer_norm1.weight": "model-00004-of-00005.safetensors",
577
+ "model.vision_encoder.encoder.layers.21.layer_norm2.bias": "model-00004-of-00005.safetensors",
578
+ "model.vision_encoder.encoder.layers.21.layer_norm2.weight": "model-00004-of-00005.safetensors",
579
+ "model.vision_encoder.encoder.layers.21.mlp.fc1.bias": "model-00004-of-00005.safetensors",
580
+ "model.vision_encoder.encoder.layers.21.mlp.fc1.weight": "model-00004-of-00005.safetensors",
581
+ "model.vision_encoder.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00005.safetensors",
582
+ "model.vision_encoder.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00005.safetensors",
583
+ "model.vision_encoder.encoder.layers.21.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
584
+ "model.vision_encoder.encoder.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
585
+ "model.vision_encoder.encoder.layers.21.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
586
+ "model.vision_encoder.encoder.layers.21.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
587
+ "model.vision_encoder.encoder.layers.21.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
588
+ "model.vision_encoder.encoder.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
589
+ "model.vision_encoder.encoder.layers.21.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
590
+ "model.vision_encoder.encoder.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
591
+ "model.vision_encoder.encoder.layers.22.layer_norm1.bias": "model-00004-of-00005.safetensors",
592
+ "model.vision_encoder.encoder.layers.22.layer_norm1.weight": "model-00004-of-00005.safetensors",
593
+ "model.vision_encoder.encoder.layers.22.layer_norm2.bias": "model-00004-of-00005.safetensors",
594
+ "model.vision_encoder.encoder.layers.22.layer_norm2.weight": "model-00004-of-00005.safetensors",
595
+ "model.vision_encoder.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00005.safetensors",
596
+ "model.vision_encoder.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00005.safetensors",
597
+ "model.vision_encoder.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00005.safetensors",
598
+ "model.vision_encoder.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00005.safetensors",
599
+ "model.vision_encoder.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
600
+ "model.vision_encoder.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
601
+ "model.vision_encoder.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
602
+ "model.vision_encoder.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
603
+ "model.vision_encoder.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
604
+ "model.vision_encoder.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
605
+ "model.vision_encoder.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
606
+ "model.vision_encoder.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
607
+ "model.vision_encoder.encoder.layers.23.layer_norm1.bias": "model-00004-of-00005.safetensors",
608
+ "model.vision_encoder.encoder.layers.23.layer_norm1.weight": "model-00004-of-00005.safetensors",
609
+ "model.vision_encoder.encoder.layers.23.layer_norm2.bias": "model-00004-of-00005.safetensors",
610
+ "model.vision_encoder.encoder.layers.23.layer_norm2.weight": "model-00004-of-00005.safetensors",
611
+ "model.vision_encoder.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00005.safetensors",
612
+ "model.vision_encoder.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00005.safetensors",
613
+ "model.vision_encoder.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00005.safetensors",
614
+ "model.vision_encoder.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00005.safetensors",
615
+ "model.vision_encoder.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
616
+ "model.vision_encoder.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
617
+ "model.vision_encoder.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
618
+ "model.vision_encoder.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
619
+ "model.vision_encoder.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
620
+ "model.vision_encoder.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
621
+ "model.vision_encoder.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
622
+ "model.vision_encoder.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
623
+ "model.vision_encoder.encoder.layers.24.layer_norm1.bias": "model-00004-of-00005.safetensors",
624
+ "model.vision_encoder.encoder.layers.24.layer_norm1.weight": "model-00004-of-00005.safetensors",
625
+ "model.vision_encoder.encoder.layers.24.layer_norm2.bias": "model-00004-of-00005.safetensors",
626
+ "model.vision_encoder.encoder.layers.24.layer_norm2.weight": "model-00004-of-00005.safetensors",
627
+ "model.vision_encoder.encoder.layers.24.mlp.fc1.bias": "model-00004-of-00005.safetensors",
628
+ "model.vision_encoder.encoder.layers.24.mlp.fc1.weight": "model-00004-of-00005.safetensors",
629
+ "model.vision_encoder.encoder.layers.24.mlp.fc2.bias": "model-00004-of-00005.safetensors",
630
+ "model.vision_encoder.encoder.layers.24.mlp.fc2.weight": "model-00004-of-00005.safetensors",
631
+ "model.vision_encoder.encoder.layers.24.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
632
+ "model.vision_encoder.encoder.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
633
+ "model.vision_encoder.encoder.layers.24.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
634
+ "model.vision_encoder.encoder.layers.24.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
635
+ "model.vision_encoder.encoder.layers.24.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
636
+ "model.vision_encoder.encoder.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
637
+ "model.vision_encoder.encoder.layers.24.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
638
+ "model.vision_encoder.encoder.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
639
+ "model.vision_encoder.encoder.layers.25.layer_norm1.bias": "model-00004-of-00005.safetensors",
640
+ "model.vision_encoder.encoder.layers.25.layer_norm1.weight": "model-00004-of-00005.safetensors",
641
+ "model.vision_encoder.encoder.layers.25.layer_norm2.bias": "model-00004-of-00005.safetensors",
642
+ "model.vision_encoder.encoder.layers.25.layer_norm2.weight": "model-00004-of-00005.safetensors",
643
+ "model.vision_encoder.encoder.layers.25.mlp.fc1.bias": "model-00004-of-00005.safetensors",
644
+ "model.vision_encoder.encoder.layers.25.mlp.fc1.weight": "model-00004-of-00005.safetensors",
645
+ "model.vision_encoder.encoder.layers.25.mlp.fc2.bias": "model-00004-of-00005.safetensors",
646
+ "model.vision_encoder.encoder.layers.25.mlp.fc2.weight": "model-00004-of-00005.safetensors",
647
+ "model.vision_encoder.encoder.layers.25.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
648
+ "model.vision_encoder.encoder.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
649
+ "model.vision_encoder.encoder.layers.25.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
650
+ "model.vision_encoder.encoder.layers.25.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
651
+ "model.vision_encoder.encoder.layers.25.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
652
+ "model.vision_encoder.encoder.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
653
+ "model.vision_encoder.encoder.layers.25.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
654
+ "model.vision_encoder.encoder.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
655
+ "model.vision_encoder.encoder.layers.26.layer_norm1.bias": "model-00004-of-00005.safetensors",
656
+ "model.vision_encoder.encoder.layers.26.layer_norm1.weight": "model-00004-of-00005.safetensors",
657
+ "model.vision_encoder.encoder.layers.26.layer_norm2.bias": "model-00004-of-00005.safetensors",
658
+ "model.vision_encoder.encoder.layers.26.layer_norm2.weight": "model-00004-of-00005.safetensors",
659
+ "model.vision_encoder.encoder.layers.26.mlp.fc1.bias": "model-00004-of-00005.safetensors",
660
+ "model.vision_encoder.encoder.layers.26.mlp.fc1.weight": "model-00004-of-00005.safetensors",
661
+ "model.vision_encoder.encoder.layers.26.mlp.fc2.bias": "model-00004-of-00005.safetensors",
662
+ "model.vision_encoder.encoder.layers.26.mlp.fc2.weight": "model-00004-of-00005.safetensors",
663
+ "model.vision_encoder.encoder.layers.26.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
664
+ "model.vision_encoder.encoder.layers.26.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
665
+ "model.vision_encoder.encoder.layers.26.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
666
+ "model.vision_encoder.encoder.layers.26.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
667
+ "model.vision_encoder.encoder.layers.26.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
668
+ "model.vision_encoder.encoder.layers.26.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
669
+ "model.vision_encoder.encoder.layers.26.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
670
+ "model.vision_encoder.encoder.layers.26.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
671
+ "model.vision_encoder.encoder.layers.3.layer_norm1.bias": "model-00004-of-00005.safetensors",
672
+ "model.vision_encoder.encoder.layers.3.layer_norm1.weight": "model-00004-of-00005.safetensors",
673
+ "model.vision_encoder.encoder.layers.3.layer_norm2.bias": "model-00004-of-00005.safetensors",
674
+ "model.vision_encoder.encoder.layers.3.layer_norm2.weight": "model-00004-of-00005.safetensors",
675
+ "model.vision_encoder.encoder.layers.3.mlp.fc1.bias": "model-00004-of-00005.safetensors",
676
+ "model.vision_encoder.encoder.layers.3.mlp.fc1.weight": "model-00004-of-00005.safetensors",
677
+ "model.vision_encoder.encoder.layers.3.mlp.fc2.bias": "model-00004-of-00005.safetensors",
678
+ "model.vision_encoder.encoder.layers.3.mlp.fc2.weight": "model-00004-of-00005.safetensors",
679
+ "model.vision_encoder.encoder.layers.3.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
680
+ "model.vision_encoder.encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
681
+ "model.vision_encoder.encoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
682
+ "model.vision_encoder.encoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
683
+ "model.vision_encoder.encoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
684
+ "model.vision_encoder.encoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
685
+ "model.vision_encoder.encoder.layers.3.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
686
+ "model.vision_encoder.encoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
687
+ "model.vision_encoder.encoder.layers.4.layer_norm1.bias": "model-00004-of-00005.safetensors",
688
+ "model.vision_encoder.encoder.layers.4.layer_norm1.weight": "model-00004-of-00005.safetensors",
689
+ "model.vision_encoder.encoder.layers.4.layer_norm2.bias": "model-00004-of-00005.safetensors",
690
+ "model.vision_encoder.encoder.layers.4.layer_norm2.weight": "model-00004-of-00005.safetensors",
691
+ "model.vision_encoder.encoder.layers.4.mlp.fc1.bias": "model-00004-of-00005.safetensors",
692
+ "model.vision_encoder.encoder.layers.4.mlp.fc1.weight": "model-00004-of-00005.safetensors",
693
+ "model.vision_encoder.encoder.layers.4.mlp.fc2.bias": "model-00004-of-00005.safetensors",
694
+ "model.vision_encoder.encoder.layers.4.mlp.fc2.weight": "model-00004-of-00005.safetensors",
695
+ "model.vision_encoder.encoder.layers.4.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
696
+ "model.vision_encoder.encoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
697
+ "model.vision_encoder.encoder.layers.4.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
698
+ "model.vision_encoder.encoder.layers.4.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
699
+ "model.vision_encoder.encoder.layers.4.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
700
+ "model.vision_encoder.encoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
701
+ "model.vision_encoder.encoder.layers.4.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
702
+ "model.vision_encoder.encoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
703
+ "model.vision_encoder.encoder.layers.5.layer_norm1.bias": "model-00004-of-00005.safetensors",
704
+ "model.vision_encoder.encoder.layers.5.layer_norm1.weight": "model-00004-of-00005.safetensors",
705
+ "model.vision_encoder.encoder.layers.5.layer_norm2.bias": "model-00004-of-00005.safetensors",
706
+ "model.vision_encoder.encoder.layers.5.layer_norm2.weight": "model-00004-of-00005.safetensors",
707
+ "model.vision_encoder.encoder.layers.5.mlp.fc1.bias": "model-00004-of-00005.safetensors",
708
+ "model.vision_encoder.encoder.layers.5.mlp.fc1.weight": "model-00004-of-00005.safetensors",
709
+ "model.vision_encoder.encoder.layers.5.mlp.fc2.bias": "model-00004-of-00005.safetensors",
710
+ "model.vision_encoder.encoder.layers.5.mlp.fc2.weight": "model-00004-of-00005.safetensors",
711
+ "model.vision_encoder.encoder.layers.5.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
712
+ "model.vision_encoder.encoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
713
+ "model.vision_encoder.encoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
714
+ "model.vision_encoder.encoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
715
+ "model.vision_encoder.encoder.layers.5.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
716
+ "model.vision_encoder.encoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
717
+ "model.vision_encoder.encoder.layers.5.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
718
+ "model.vision_encoder.encoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
719
+ "model.vision_encoder.encoder.layers.6.layer_norm1.bias": "model-00004-of-00005.safetensors",
720
+ "model.vision_encoder.encoder.layers.6.layer_norm1.weight": "model-00004-of-00005.safetensors",
721
+ "model.vision_encoder.encoder.layers.6.layer_norm2.bias": "model-00004-of-00005.safetensors",
722
+ "model.vision_encoder.encoder.layers.6.layer_norm2.weight": "model-00004-of-00005.safetensors",
723
+ "model.vision_encoder.encoder.layers.6.mlp.fc1.bias": "model-00004-of-00005.safetensors",
724
+ "model.vision_encoder.encoder.layers.6.mlp.fc1.weight": "model-00004-of-00005.safetensors",
725
+ "model.vision_encoder.encoder.layers.6.mlp.fc2.bias": "model-00004-of-00005.safetensors",
726
+ "model.vision_encoder.encoder.layers.6.mlp.fc2.weight": "model-00004-of-00005.safetensors",
727
+ "model.vision_encoder.encoder.layers.6.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
728
+ "model.vision_encoder.encoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
729
+ "model.vision_encoder.encoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
730
+ "model.vision_encoder.encoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
731
+ "model.vision_encoder.encoder.layers.6.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
732
+ "model.vision_encoder.encoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
733
+ "model.vision_encoder.encoder.layers.6.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
734
+ "model.vision_encoder.encoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
735
+ "model.vision_encoder.encoder.layers.7.layer_norm1.bias": "model-00004-of-00005.safetensors",
736
+ "model.vision_encoder.encoder.layers.7.layer_norm1.weight": "model-00004-of-00005.safetensors",
737
+ "model.vision_encoder.encoder.layers.7.layer_norm2.bias": "model-00004-of-00005.safetensors",
738
+ "model.vision_encoder.encoder.layers.7.layer_norm2.weight": "model-00004-of-00005.safetensors",
739
+ "model.vision_encoder.encoder.layers.7.mlp.fc1.bias": "model-00004-of-00005.safetensors",
740
+ "model.vision_encoder.encoder.layers.7.mlp.fc1.weight": "model-00004-of-00005.safetensors",
741
+ "model.vision_encoder.encoder.layers.7.mlp.fc2.bias": "model-00004-of-00005.safetensors",
742
+ "model.vision_encoder.encoder.layers.7.mlp.fc2.weight": "model-00004-of-00005.safetensors",
743
+ "model.vision_encoder.encoder.layers.7.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
744
+ "model.vision_encoder.encoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
745
+ "model.vision_encoder.encoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
746
+ "model.vision_encoder.encoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
747
+ "model.vision_encoder.encoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
748
+ "model.vision_encoder.encoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
749
+ "model.vision_encoder.encoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
750
+ "model.vision_encoder.encoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
751
+ "model.vision_encoder.encoder.layers.8.layer_norm1.bias": "model-00004-of-00005.safetensors",
752
+ "model.vision_encoder.encoder.layers.8.layer_norm1.weight": "model-00004-of-00005.safetensors",
753
+ "model.vision_encoder.encoder.layers.8.layer_norm2.bias": "model-00004-of-00005.safetensors",
754
+ "model.vision_encoder.encoder.layers.8.layer_norm2.weight": "model-00004-of-00005.safetensors",
755
+ "model.vision_encoder.encoder.layers.8.mlp.fc1.bias": "model-00004-of-00005.safetensors",
756
+ "model.vision_encoder.encoder.layers.8.mlp.fc1.weight": "model-00004-of-00005.safetensors",
757
+ "model.vision_encoder.encoder.layers.8.mlp.fc2.bias": "model-00004-of-00005.safetensors",
758
+ "model.vision_encoder.encoder.layers.8.mlp.fc2.weight": "model-00004-of-00005.safetensors",
759
+ "model.vision_encoder.encoder.layers.8.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
760
+ "model.vision_encoder.encoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
761
+ "model.vision_encoder.encoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
762
+ "model.vision_encoder.encoder.layers.8.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
763
+ "model.vision_encoder.encoder.layers.8.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
764
+ "model.vision_encoder.encoder.layers.8.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
765
+ "model.vision_encoder.encoder.layers.8.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
766
+ "model.vision_encoder.encoder.layers.8.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
767
+ "model.vision_encoder.encoder.layers.9.layer_norm1.bias": "model-00004-of-00005.safetensors",
768
+ "model.vision_encoder.encoder.layers.9.layer_norm1.weight": "model-00004-of-00005.safetensors",
769
+ "model.vision_encoder.encoder.layers.9.layer_norm2.bias": "model-00004-of-00005.safetensors",
770
+ "model.vision_encoder.encoder.layers.9.layer_norm2.weight": "model-00004-of-00005.safetensors",
771
+ "model.vision_encoder.encoder.layers.9.mlp.fc1.bias": "model-00004-of-00005.safetensors",
772
+ "model.vision_encoder.encoder.layers.9.mlp.fc1.weight": "model-00004-of-00005.safetensors",
773
+ "model.vision_encoder.encoder.layers.9.mlp.fc2.bias": "model-00004-of-00005.safetensors",
774
+ "model.vision_encoder.encoder.layers.9.mlp.fc2.weight": "model-00004-of-00005.safetensors",
775
+ "model.vision_encoder.encoder.layers.9.self_attn.k_proj.bias": "model-00004-of-00005.safetensors",
776
+ "model.vision_encoder.encoder.layers.9.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
777
+ "model.vision_encoder.encoder.layers.9.self_attn.out_proj.bias": "model-00004-of-00005.safetensors",
778
+ "model.vision_encoder.encoder.layers.9.self_attn.out_proj.weight": "model-00004-of-00005.safetensors",
779
+ "model.vision_encoder.encoder.layers.9.self_attn.q_proj.bias": "model-00004-of-00005.safetensors",
780
+ "model.vision_encoder.encoder.layers.9.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
781
+ "model.vision_encoder.encoder.layers.9.self_attn.v_proj.bias": "model-00004-of-00005.safetensors",
782
+ "model.vision_encoder.encoder.layers.9.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
783
+ "model.vision_encoder.post_layernorm.bias": "model-00004-of-00005.safetensors",
784
+ "model.vision_encoder.post_layernorm.weight": "model-00004-of-00005.safetensors"
785
+ }
786
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_map": {
3
+ "AutoImageProcessor": "DAMO-NLP-SG/VideoLLaMA3-7B-Image--image_processing_videollama3.Videollama3ImageProcessor",
4
+ "AutoProcessor": "DAMO-NLP-SG/VideoLLaMA3-7B-Image--processing_videollama3.Videollama3Qwen2Processor"
5
+ },
6
+ "do_convert_rgb": true,
7
+ "do_normalize": true,
8
+ "do_rescale": true,
9
+ "do_resize": true,
10
+ "image_mean": [
11
+ 0.5,
12
+ 0.5,
13
+ 0.5
14
+ ],
15
+ "image_processor_type": "Videollama3ImageProcessor",
16
+ "image_std": [
17
+ 0.5,
18
+ 0.5,
19
+ 0.5
20
+ ],
21
+ "max_tokens": 16384,
22
+ "min_tokens": 16,
23
+ "patch_size": 14,
24
+ "processor_class": "Videollama3Qwen2Processor",
25
+ "resample": 3,
26
+ "rescale_factor": 0.00392156862745098
27
+ }
processor_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "fps": 1,
3
+ "image_merge_size": 1,
4
+ "max_frames": 128,
5
+ "processor_class": "Videollama3Qwen2Processor",
6
+ "video_merge_size": 2
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bb63ceb1524412064763cffa446ec94ca752b2be438213ddf3242c36a6152a1
3
+ size 11422458
tokenizer_config.json ADDED
@@ -0,0 +1,237 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<image>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|stream_start|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<|stream_end|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ }
205
+ },
206
+ "additional_special_tokens": [
207
+ "<|im_start|>",
208
+ "<|im_end|>",
209
+ "<|object_ref_start|>",
210
+ "<|object_ref_end|>",
211
+ "<|box_start|>",
212
+ "<|box_end|>",
213
+ "<|quad_start|>",
214
+ "<|quad_end|>",
215
+ "<|vision_start|>",
216
+ "<|vision_end|>",
217
+ "<|vision_pad|>",
218
+ "<|image_pad|>",
219
+ "<|video_pad|>"
220
+ ],
221
+ "auto_map": {
222
+ "AutoProcessor": "DAMO-NLP-SG/VideoLLaMA3-7B-Image--processing_videollama3.Videollama3Qwen2Processor"
223
+ },
224
+ "bos_token": null,
225
+ "chat_template": "\n{%- set identifier = 'im' %}\n{% for message in messages %}\n {% if add_system_prompt and loop.first and message['role'] != 'system' %}\n {{- '<|im_start|>system\nYou are VideoLLaMA3 created by Alibaba DAMO Academy, a helpful assistant to help people understand images and videos.<|im_end|>\n' -}}\n {% endif %}\n {% if message['role'] == 'stream' %}\n {% set identifier = 'stream' %}\n {% else %}\n {% set identifier = 'im' %}\n {% endif %}\n {{- '<|' + identifier + '_start|>' + message['role'] + '\n' -}}\n {% if message['content'] is string %}\n {{- message['content'] + '<|' + identifier + '_end|>\n' -}}\n {% else %}\n {% for content in message['content'] %}\n {% if content is string %}\n {{- content -}}\n {% elif content['type'] == 'text' or 'text' in content %}\n {{- content['text'] -}}\n {% elif content['type'] == 'image' or 'image' in content %}\n {% if 'timestamp' in content %}\n {{- 'Time ' + content['timestamp'] | round(1) | string + 's: ' -}}\n {% endif %}\n {{- image_token + '\n' -}}\n {% elif content['type'] == 'video' or 'video' in content %}\n {% for i in range(content['num_frames']) %}\n {% if 'timestamps' in content %}\n {{- 'Time ' + content['timestamps'][i] | round(1) | string + 's:' -}}\n {% endif %}\n {% if i < content['num_frames'] - 1 %}\n {{- image_token + ',' -}}\n {% else %}\n {{- image_token + '\n' -}}\n {% endif %}\n {% endfor %}\n {% endif %}\n {% endfor %}\n {% if identifier == 'stream' %}\n {{- '<|' + identifier + '_end|>' -}}\n {% else %}\n {{- '<|' + identifier + '_end|>\n' -}}\n {% endif %}\n {% endif %}\n{% endfor %}\n{% if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' -}}\n{% endif %}\n",
226
+ "clean_up_tokenization_spaces": false,
227
+ "eos_token": "<|im_end|>",
228
+ "errors": "replace",
229
+ "extra_special_tokens": {},
230
+ "model_max_length": 32768,
231
+ "pad_token": "<|endoftext|>",
232
+ "padding_side": "right",
233
+ "processor_class": "Videollama3Qwen2Processor",
234
+ "split_special_tokens": false,
235
+ "tokenizer_class": "Qwen2Tokenizer",
236
+ "unk_token": null
237
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff