Hugging Face's logo

PaDT-MLLM
/
PaDT_Pro_3B

Any-to-Any
Transformers
Safetensors
English
Chinese
qwen2_5_vl
text-generation
text-generation-inference
Model card Files
xet
Community
1
PaDT-MLLM commited on
Commit
6580a79
·
verified ·
1 Parent(s): 0ecb3a8

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +295 -0
  3. chat_template.json +3 -0
  4. config.json +76 -0
  5. generation_config.json +12 -0
  6. merges.txt +0 -0
  7. model-00001-of-00002.safetensors +3 -0
  8. model-00002-of-00002.safetensors +3 -0
  9. model.safetensors.index.json +964 -0
  10. preprocessor_config.json +29 -0
  11. special_tokens_map.json +31 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +209 -0
  14. training_args.bin +3 -0
  15. 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 +1,295 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|empty_token_0|>": 151665,
7
+ "<|empty_token_100|>": 151765,
8
+ "<|empty_token_101|>": 151766,
9
+ "<|empty_token_102|>": 151767,
10
+ "<|empty_token_103|>": 151768,
11
+ "<|empty_token_104|>": 151769,
12
+ "<|empty_token_105|>": 151770,
13
+ "<|empty_token_106|>": 151771,
14
+ "<|empty_token_107|>": 151772,
15
+ "<|empty_token_108|>": 151773,
16
+ "<|empty_token_109|>": 151774,
17
+ "<|empty_token_10|>": 151675,
18
+ "<|empty_token_110|>": 151775,
19
+ "<|empty_token_111|>": 151776,
20
+ "<|empty_token_112|>": 151777,
21
+ "<|empty_token_113|>": 151778,
22
+ "<|empty_token_114|>": 151779,
23
+ "<|empty_token_115|>": 151780,
24
+ "<|empty_token_116|>": 151781,
25
+ "<|empty_token_117|>": 151782,
26
+ "<|empty_token_118|>": 151783,
27
+ "<|empty_token_119|>": 151784,
28
+ "<|empty_token_11|>": 151676,
29
+ "<|empty_token_120|>": 151785,
30
+ "<|empty_token_121|>": 151786,
31
+ "<|empty_token_122|>": 151787,
32
+ "<|empty_token_123|>": 151788,
33
+ "<|empty_token_124|>": 151789,
34
+ "<|empty_token_125|>": 151790,
35
+ "<|empty_token_126|>": 151791,
36
+ "<|empty_token_127|>": 151792,
37
+ "<|empty_token_128|>": 151793,
38
+ "<|empty_token_129|>": 151794,
39
+ "<|empty_token_12|>": 151677,
40
+ "<|empty_token_130|>": 151795,
41
+ "<|empty_token_131|>": 151796,
42
+ "<|empty_token_132|>": 151797,
43
+ "<|empty_token_133|>": 151798,
44
+ "<|empty_token_134|>": 151799,
45
+ "<|empty_token_135|>": 151800,
46
+ "<|empty_token_136|>": 151801,
47
+ "<|empty_token_137|>": 151802,
48
+ "<|empty_token_138|>": 151803,
49
+ "<|empty_token_139|>": 151804,
50
+ "<|empty_token_13|>": 151678,
51
+ "<|empty_token_140|>": 151805,
52
+ "<|empty_token_141|>": 151806,
53
+ "<|empty_token_142|>": 151807,
54
+ "<|empty_token_143|>": 151808,
55
+ "<|empty_token_144|>": 151809,
56
+ "<|empty_token_145|>": 151810,
57
+ "<|empty_token_146|>": 151811,
58
+ "<|empty_token_147|>": 151812,
59
+ "<|empty_token_148|>": 151813,
60
+ "<|empty_token_149|>": 151814,
61
+ "<|empty_token_14|>": 151679,
62
+ "<|empty_token_150|>": 151815,
63
+ "<|empty_token_151|>": 151816,
64
+ "<|empty_token_152|>": 151817,
65
+ "<|empty_token_153|>": 151818,
66
+ "<|empty_token_154|>": 151819,
67
+ "<|empty_token_155|>": 151820,
68
+ "<|empty_token_156|>": 151821,
69
+ "<|empty_token_157|>": 151822,
70
+ "<|empty_token_158|>": 151823,
71
+ "<|empty_token_159|>": 151824,
72
+ "<|empty_token_15|>": 151680,
73
+ "<|empty_token_160|>": 151825,
74
+ "<|empty_token_161|>": 151826,
75
+ "<|empty_token_162|>": 151827,
76
+ "<|empty_token_163|>": 151828,
77
+ "<|empty_token_164|>": 151829,
78
+ "<|empty_token_165|>": 151830,
79
+ "<|empty_token_166|>": 151831,
80
+ "<|empty_token_167|>": 151832,
81
+ "<|empty_token_168|>": 151833,
82
+ "<|empty_token_169|>": 151834,
83
+ "<|empty_token_16|>": 151681,
84
+ "<|empty_token_170|>": 151835,
85
+ "<|empty_token_171|>": 151836,
86
+ "<|empty_token_172|>": 151837,
87
+ "<|empty_token_173|>": 151838,
88
+ "<|empty_token_174|>": 151839,
89
+ "<|empty_token_175|>": 151840,
90
+ "<|empty_token_176|>": 151841,
91
+ "<|empty_token_177|>": 151842,
92
+ "<|empty_token_178|>": 151843,
93
+ "<|empty_token_179|>": 151844,
94
+ "<|empty_token_17|>": 151682,
95
+ "<|empty_token_180|>": 151845,
96
+ "<|empty_token_181|>": 151846,
97
+ "<|empty_token_182|>": 151847,
98
+ "<|empty_token_183|>": 151848,
99
+ "<|empty_token_184|>": 151849,
100
+ "<|empty_token_185|>": 151850,
101
+ "<|empty_token_186|>": 151851,
102
+ "<|empty_token_187|>": 151852,
103
+ "<|empty_token_188|>": 151853,
104
+ "<|empty_token_189|>": 151854,
105
+ "<|empty_token_18|>": 151683,
106
+ "<|empty_token_190|>": 151855,
107
+ "<|empty_token_191|>": 151856,
108
+ "<|empty_token_192|>": 151857,
109
+ "<|empty_token_193|>": 151858,
110
+ "<|empty_token_194|>": 151859,
111
+ "<|empty_token_195|>": 151860,
112
+ "<|empty_token_196|>": 151861,
113
+ "<|empty_token_197|>": 151862,
114
+ "<|empty_token_198|>": 151863,
115
+ "<|empty_token_199|>": 151864,
116
+ "<|empty_token_19|>": 151684,
117
+ "<|empty_token_1|>": 151666,
118
+ "<|empty_token_200|>": 151865,
119
+ "<|empty_token_201|>": 151866,
120
+ "<|empty_token_202|>": 151867,
121
+ "<|empty_token_203|>": 151868,
122
+ "<|empty_token_204|>": 151869,
123
+ "<|empty_token_205|>": 151870,
124
+ "<|empty_token_206|>": 151871,
125
+ "<|empty_token_207|>": 151872,
126
+ "<|empty_token_208|>": 151873,
127
+ "<|empty_token_209|>": 151874,
128
+ "<|empty_token_20|>": 151685,
129
+ "<|empty_token_210|>": 151875,
130
+ "<|empty_token_211|>": 151876,
131
+ "<|empty_token_212|>": 151877,
132
+ "<|empty_token_213|>": 151878,
133
+ "<|empty_token_214|>": 151879,
134
+ "<|empty_token_215|>": 151880,
135
+ "<|empty_token_216|>": 151881,
136
+ "<|empty_token_217|>": 151882,
137
+ "<|empty_token_218|>": 151883,
138
+ "<|empty_token_219|>": 151884,
139
+ "<|empty_token_21|>": 151686,
140
+ "<|empty_token_220|>": 151885,
141
+ "<|empty_token_221|>": 151886,
142
+ "<|empty_token_222|>": 151887,
143
+ "<|empty_token_223|>": 151888,
144
+ "<|empty_token_224|>": 151889,
145
+ "<|empty_token_225|>": 151890,
146
+ "<|empty_token_226|>": 151891,
147
+ "<|empty_token_227|>": 151892,
148
+ "<|empty_token_228|>": 151893,
149
+ "<|empty_token_229|>": 151894,
150
+ "<|empty_token_22|>": 151687,
151
+ "<|empty_token_230|>": 151895,
152
+ "<|empty_token_231|>": 151896,
153
+ "<|empty_token_232|>": 151897,
154
+ "<|empty_token_233|>": 151898,
155
+ "<|empty_token_234|>": 151899,
156
+ "<|empty_token_235|>": 151900,
157
+ "<|empty_token_236|>": 151901,
158
+ "<|empty_token_237|>": 151902,
159
+ "<|empty_token_238|>": 151903,
160
+ "<|empty_token_239|>": 151904,
161
+ "<|empty_token_23|>": 151688,
162
+ "<|empty_token_240|>": 151905,
163
+ "<|empty_token_241|>": 151906,
164
+ "<|empty_token_242|>": 151907,
165
+ "<|empty_token_243|>": 151908,
166
+ "<|empty_token_244|>": 151909,
167
+ "<|empty_token_245|>": 151910,
168
+ "<|empty_token_246|>": 151911,
169
+ "<|empty_token_247|>": 151912,
170
+ "<|empty_token_248|>": 151913,
171
+ "<|empty_token_249|>": 151914,
172
+ "<|empty_token_24|>": 151689,
173
+ "<|empty_token_250|>": 151915,
174
+ "<|empty_token_251|>": 151916,
175
+ "<|empty_token_252|>": 151917,
176
+ "<|empty_token_253|>": 151918,
177
+ "<|empty_token_254|>": 151919,
178
+ "<|empty_token_255|>": 151920,
179
+ "<|empty_token_256|>": 151921,
180
+ "<|empty_token_257|>": 151922,
181
+ "<|empty_token_258|>": 151923,
182
+ "<|empty_token_259|>": 151924,
183
+ "<|empty_token_25|>": 151690,
184
+ "<|empty_token_260|>": 151925,
185
+ "<|empty_token_261|>": 151926,
186
+ "<|empty_token_262|>": 151927,
187
+ "<|empty_token_263|>": 151928,
188
+ "<|empty_token_264|>": 151929,
189
+ "<|empty_token_265|>": 151930,
190
+ "<|empty_token_266|>": 151931,
191
+ "<|empty_token_267|>": 151932,
192
+ "<|empty_token_268|>": 151933,
193
+ "<|empty_token_269|>": 151934,
194
+ "<|empty_token_26|>": 151691,
195
+ "<|empty_token_270|>": 151935,
196
+ "<|empty_token_27|>": 151692,
197
+ "<|empty_token_28|>": 151693,
198
+ "<|empty_token_29|>": 151694,
199
+ "<|empty_token_2|>": 151667,
200
+ "<|empty_token_30|>": 151695,
201
+ "<|empty_token_31|>": 151696,
202
+ "<|empty_token_32|>": 151697,
203
+ "<|empty_token_33|>": 151698,
204
+ "<|empty_token_34|>": 151699,
205
+ "<|empty_token_35|>": 151700,
206
+ "<|empty_token_36|>": 151701,
207
+ "<|empty_token_37|>": 151702,
208
+ "<|empty_token_38|>": 151703,
209
+ "<|empty_token_39|>": 151704,
210
+ "<|empty_token_3|>": 151668,
211
+ "<|empty_token_40|>": 151705,
212
+ "<|empty_token_41|>": 151706,
213
+ "<|empty_token_42|>": 151707,
214
+ "<|empty_token_43|>": 151708,
215
+ "<|empty_token_44|>": 151709,
216
+ "<|empty_token_45|>": 151710,
217
+ "<|empty_token_46|>": 151711,
218
+ "<|empty_token_47|>": 151712,
219
+ "<|empty_token_48|>": 151713,
220
+ "<|empty_token_49|>": 151714,
221
+ "<|empty_token_4|>": 151669,
222
+ "<|empty_token_50|>": 151715,
223
+ "<|empty_token_51|>": 151716,
224
+ "<|empty_token_52|>": 151717,
225
+ "<|empty_token_53|>": 151718,
226
+ "<|empty_token_54|>": 151719,
227
+ "<|empty_token_55|>": 151720,
228
+ "<|empty_token_56|>": 151721,
229
+ "<|empty_token_57|>": 151722,
230
+ "<|empty_token_58|>": 151723,
231
+ "<|empty_token_59|>": 151724,
232
+ "<|empty_token_5|>": 151670,
233
+ "<|empty_token_60|>": 151725,
234
+ "<|empty_token_61|>": 151726,
235
+ "<|empty_token_62|>": 151727,
236
+ "<|empty_token_63|>": 151728,
237
+ "<|empty_token_64|>": 151729,
238
+ "<|empty_token_65|>": 151730,
239
+ "<|empty_token_66|>": 151731,
240
+ "<|empty_token_67|>": 151732,
241
+ "<|empty_token_68|>": 151733,
242
+ "<|empty_token_69|>": 151734,
243
+ "<|empty_token_6|>": 151671,
244
+ "<|empty_token_70|>": 151735,
245
+ "<|empty_token_71|>": 151736,
246
+ "<|empty_token_72|>": 151737,
247
+ "<|empty_token_73|>": 151738,
248
+ "<|empty_token_74|>": 151739,
249
+ "<|empty_token_75|>": 151740,
250
+ "<|empty_token_76|>": 151741,
251
+ "<|empty_token_77|>": 151742,
252
+ "<|empty_token_78|>": 151743,
253
+ "<|empty_token_79|>": 151744,
254
+ "<|empty_token_7|>": 151672,
255
+ "<|empty_token_80|>": 151745,
256
+ "<|empty_token_81|>": 151746,
257
+ "<|empty_token_82|>": 151747,
258
+ "<|empty_token_83|>": 151748,
259
+ "<|empty_token_84|>": 151749,
260
+ "<|empty_token_85|>": 151750,
261
+ "<|empty_token_86|>": 151751,
262
+ "<|empty_token_87|>": 151752,
263
+ "<|empty_token_88|>": 151753,
264
+ "<|empty_token_89|>": 151754,
265
+ "<|empty_token_8|>": 151673,
266
+ "<|empty_token_90|>": 151755,
267
+ "<|empty_token_91|>": 151756,
268
+ "<|empty_token_92|>": 151757,
269
+ "<|empty_token_93|>": 151758,
270
+ "<|empty_token_94|>": 151759,
271
+ "<|empty_token_95|>": 151760,
272
+ "<|empty_token_96|>": 151761,
273
+ "<|empty_token_97|>": 151762,
274
+ "<|empty_token_98|>": 151763,
275
+ "<|empty_token_99|>": 151764,
276
+ "<|empty_token_9|>": 151674,
277
+ "<|endoftext|>": 151643,
278
+ "<|file_sep|>": 151664,
279
+ "<|fim_middle|>": 151660,
280
+ "<|fim_pad|>": 151662,
281
+ "<|fim_prefix|>": 151659,
282
+ "<|fim_suffix|>": 151661,
283
+ "<|im_end|>": 151645,
284
+ "<|im_start|>": 151644,
285
+ "<|image_pad|>": 151655,
286
+ "<|object_ref_end|>": 151647,
287
+ "<|object_ref_start|>": 151646,
288
+ "<|quad_end|>": 151651,
289
+ "<|quad_start|>": 151650,
290
+ "<|repo_name|>": 151663,
291
+ "<|video_pad|>": 151656,
292
+ "<|vision_end|>": 151653,
293
+ "<|vision_pad|>": 151654,
294
+ "<|vision_start|>": 151652
295
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "PaDTForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 2048,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 36,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "mrope_section": [
22
+ 16,
23
+ 24,
24
+ 24
25
+ ],
26
+ "rope_type": "default",
27
+ "type": "default"
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "tie_word_embeddings": true,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.50.0",
34
+ "use_cache": false,
35
+ "use_sliding_window": false,
36
+ "use_visual_prototype_projection": true,
37
+ "video_token_id": 151656,
38
+ "vision_config": {
39
+ "depth": 32,
40
+ "fullatt_block_indexes": [
41
+ 7,
42
+ 15,
43
+ 23,
44
+ 31
45
+ ],
46
+ "hidden_act": "silu",
47
+ "hidden_size": 1280,
48
+ "in_channels": 3,
49
+ "in_chans": 3,
50
+ "intermediate_size": 3420,
51
+ "model_type": "qwen2_5_vl",
52
+ "num_heads": 16,
53
+ "out_hidden_size": 2048,
54
+ "patch_size": 14,
55
+ "spatial_merge_size": 2,
56
+ "spatial_patch_size": 14,
57
+ "temporal_patch_size": 2,
58
+ "tokens_per_second": 2,
59
+ "torch_dtype": "bfloat16",
60
+ "window_size": 112
61
+ },
62
+ "vision_end_token_id": 151653,
63
+ "vision_start_token_id": 151652,
64
+ "vision_token_id": 151654,
65
+ "vl_decoder": {
66
+ "attn_implementation": "flash_attention_2",
67
+ "hidden_size": 1280,
68
+ "intermediate_size": 3420,
69
+ "llm_hidden_state": 2048,
70
+ "name": "PaDTDecoder",
71
+ "num_heads": 16,
72
+ "spatial_merge_size": 2,
73
+ "use_mask_loss": true
74
+ },
75
+ "vocab_size": 151936
76
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 1e-06,
11
+ "transformers_version": "4.50.0"
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a7e5d985f67e5b5f99be56a7e60c7a3486fdb014e626e5b585c0004731a4532
3
+ size 4997750760
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be1d70de376e529c9f12aa329f734a118de3730eae89eee178d1311660557a8e
3
+ size 2708163450
model.safetensors.index.json ADDED
@@ -0,0 +1,964 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7705805138
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
42
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
49
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
52
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
54
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
61
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
64
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
66
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
73
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
76
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
78
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
85
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
88
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
90
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
97
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
100
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
102
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
109
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
112
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
114
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
121
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
124
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
126
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
133
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
136
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
138
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
140
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
141
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
145
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
148
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
150
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
157
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
160
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
162
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
163
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
169
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
172
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
174
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
181
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
184
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
186
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
193
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
196
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
198
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
205
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
208
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
210
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
216
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
217
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
218
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
220
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
222
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
223
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
224
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
229
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
232
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
234
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
241
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
244
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
245
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
246
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
248
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
251
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
252
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
253
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
255
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
256
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
258
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
259
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
260
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
262
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
263
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
264
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
265
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
266
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
267
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
268
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
269
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
270
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
271
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
272
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
273
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
276
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
277
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
278
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
280
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
281
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
282
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
289
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
292
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
294
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
296
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
299
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
300
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
301
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
303
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
304
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
306
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
308
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
310
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
311
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
312
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
313
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
314
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
316
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
317
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
318
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
320
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
321
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
322
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
324
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
325
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
328
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
330
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
332
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
333
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
336
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
337
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
339
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
340
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
341
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
342
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
343
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
344
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
345
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
346
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
347
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
348
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
349
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
350
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
351
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
352
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
353
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
354
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
355
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
356
+ "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
357
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
358
+ "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
359
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
360
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
361
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
362
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
363
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
364
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
365
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
366
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
367
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
368
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
369
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
373
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
376
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
377
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
378
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
380
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
383
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
384
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
385
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
387
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
388
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
390
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
391
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
392
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
394
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
396
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
397
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
398
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
399
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
400
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
402
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
404
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
405
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
406
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
408
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
409
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
410
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
411
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
412
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
413
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
414
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
415
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
416
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
417
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
420
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
421
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
422
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
423
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
424
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
425
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
426
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
427
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
428
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
429
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
430
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
432
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
433
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
434
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
435
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
436
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
437
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
438
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
439
+ "model.norm.weight": "model-00002-of-00002.safetensors",
440
+ "vis_norm.bias": "model-00002-of-00002.safetensors",
441
+ "vis_norm.weight": "model-00002-of-00002.safetensors",
442
+ "vis_proj.0.weight": "model-00002-of-00002.safetensors",
443
+ "vis_proj.1.weight": "model-00002-of-00002.safetensors",
444
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
445
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
446
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
447
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
448
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
449
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
450
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
451
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
452
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
453
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
454
+ "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
455
+ "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
456
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
457
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
458
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
459
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
460
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
461
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
462
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
463
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
464
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
465
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
466
+ "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
467
+ "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
468
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
469
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
470
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
471
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
472
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
473
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
474
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
475
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
476
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
477
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
478
+ "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
479
+ "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
480
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
481
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
482
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
483
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
484
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
485
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
486
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
487
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
488
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
489
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
490
+ "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
491
+ "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
492
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
493
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
494
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
495
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
496
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
497
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
498
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
499
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
500
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
501
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
502
+ "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
503
+ "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
504
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
505
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
506
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
507
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
508
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
509
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
510
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
511
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
512
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
513
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
514
+ "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
515
+ "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
516
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
517
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
518
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
519
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
520
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
521
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
522
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
523
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
524
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
525
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
526
+ "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
527
+ "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
528
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
529
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
530
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
531
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
532
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
533
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
534
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
535
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
536
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
537
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
538
+ "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
539
+ "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
540
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
541
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
542
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
543
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
544
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
545
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
546
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
547
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
548
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
549
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
550
+ "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
551
+ "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
552
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
553
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
554
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
555
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
556
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
557
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
558
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
559
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
560
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
561
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
562
+ "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
563
+ "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
564
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
565
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
566
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
567
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
568
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
569
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
570
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
571
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
572
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
573
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
574
+ "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
575
+ "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
576
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
577
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
578
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
579
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
580
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
581
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
582
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
583
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
584
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
585
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
586
+ "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
587
+ "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
588
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
589
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
590
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
591
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
592
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
593
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
594
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
595
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
596
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
597
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
598
+ "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
599
+ "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
600
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
601
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
602
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
603
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
604
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
605
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
606
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
607
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
608
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
609
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
610
+ "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
611
+ "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
612
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
613
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
614
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
615
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
616
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
617
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
618
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
619
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
620
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
621
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
622
+ "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
623
+ "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
624
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
625
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
626
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
627
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
628
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
629
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
630
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
631
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
632
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
633
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
634
+ "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
635
+ "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
636
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
637
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
638
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
639
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
640
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
641
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
642
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
643
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
644
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
645
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
646
+ "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
647
+ "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
648
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
649
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
650
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
651
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
652
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
653
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
654
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
655
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
656
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
657
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
658
+ "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
659
+ "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
660
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
661
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
662
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
663
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
664
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
665
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
666
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
667
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
668
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
669
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
670
+ "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
671
+ "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
672
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
673
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
674
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
675
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
676
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
677
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
678
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
679
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
680
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
681
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
682
+ "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
683
+ "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
684
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
685
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
686
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
687
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
688
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
689
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
690
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
691
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
692
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
693
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
694
+ "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
695
+ "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
696
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
697
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
698
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
699
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
700
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
701
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
702
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
703
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
704
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
705
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
706
+ "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
707
+ "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
708
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
709
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
710
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
711
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
712
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
713
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
714
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
715
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
716
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
717
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
718
+ "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
719
+ "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
720
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
721
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
722
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
723
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
724
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
725
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
726
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
727
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
728
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
729
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
730
+ "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
731
+ "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
732
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
733
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
734
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
735
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
736
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
737
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
738
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
739
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
740
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
741
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
742
+ "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
743
+ "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
744
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
745
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
746
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
747
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
748
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
749
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
750
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
751
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
752
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
753
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
754
+ "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
755
+ "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
756
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
757
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
758
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
759
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
760
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
761
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
762
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
763
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
764
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
765
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
766
+ "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
767
+ "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
768
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
769
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
770
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
771
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
772
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
773
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
774
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
775
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
776
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
777
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
778
+ "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
779
+ "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
780
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
781
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
782
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
783
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
784
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
785
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
786
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
787
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
788
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
789
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
790
+ "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
791
+ "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
792
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
793
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
794
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
795
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
796
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
797
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
798
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
799
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
800
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
801
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
802
+ "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
803
+ "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
804
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
805
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
806
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
807
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
808
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
809
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
810
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
811
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
812
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
813
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
814
+ "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
815
+ "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
816
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
817
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
818
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
819
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
820
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
821
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
822
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
823
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
824
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
825
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
826
+ "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
827
+ "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
828
+ "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
829
+ "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
830
+ "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
831
+ "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
832
+ "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
833
+ "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
834
+ "vl_decoder.bbox_prediction.0.bias": "model-00002-of-00002.safetensors",
835
+ "vl_decoder.bbox_prediction.0.weight": "model-00002-of-00002.safetensors",
836
+ "vl_decoder.bbox_prediction.2.bias": "model-00002-of-00002.safetensors",
837
+ "vl_decoder.bbox_prediction.2.weight": "model-00002-of-00002.safetensors",
838
+ "vl_decoder.bbox_prediction.4.bias": "model-00002-of-00002.safetensors",
839
+ "vl_decoder.bbox_prediction.4.weight": "model-00002-of-00002.safetensors",
840
+ "vl_decoder.bbox_score_mask_tokens.weight": "model-00002-of-00002.safetensors",
841
+ "vl_decoder.high_res_norm.weight": "model-00002-of-00002.safetensors",
842
+ "vl_decoder.high_res_transformer1.cross_attn_image_to_query.k_proj.bias": "model-00002-of-00002.safetensors",
843
+ "vl_decoder.high_res_transformer1.cross_attn_image_to_query.k_proj.weight": "model-00002-of-00002.safetensors",
844
+ "vl_decoder.high_res_transformer1.cross_attn_image_to_query.proj.bias": "model-00002-of-00002.safetensors",
845
+ "vl_decoder.high_res_transformer1.cross_attn_image_to_query.proj.weight": "model-00002-of-00002.safetensors",
846
+ "vl_decoder.high_res_transformer1.cross_attn_image_to_query.q_proj.bias": "model-00002-of-00002.safetensors",
847
+ "vl_decoder.high_res_transformer1.cross_attn_image_to_query.q_proj.weight": "model-00002-of-00002.safetensors",
848
+ "vl_decoder.high_res_transformer1.cross_attn_image_to_query.v_proj.bias": "model-00002-of-00002.safetensors",
849
+ "vl_decoder.high_res_transformer1.cross_attn_image_to_query.v_proj.weight": "model-00002-of-00002.safetensors",
850
+ "vl_decoder.high_res_transformer1.cross_attn_query_to_image.k_proj.bias": "model-00002-of-00002.safetensors",
851
+ "vl_decoder.high_res_transformer1.cross_attn_query_to_image.k_proj.weight": "model-00002-of-00002.safetensors",
852
+ "vl_decoder.high_res_transformer1.cross_attn_query_to_image.proj.bias": "model-00002-of-00002.safetensors",
853
+ "vl_decoder.high_res_transformer1.cross_attn_query_to_image.proj.weight": "model-00002-of-00002.safetensors",
854
+ "vl_decoder.high_res_transformer1.cross_attn_query_to_image.q_proj.bias": "model-00002-of-00002.safetensors",
855
+ "vl_decoder.high_res_transformer1.cross_attn_query_to_image.q_proj.weight": "model-00002-of-00002.safetensors",
856
+ "vl_decoder.high_res_transformer1.cross_attn_query_to_image.v_proj.bias": "model-00002-of-00002.safetensors",
857
+ "vl_decoder.high_res_transformer1.cross_attn_query_to_image.v_proj.weight": "model-00002-of-00002.safetensors",
858
+ "vl_decoder.high_res_transformer1.mlp.0.bias": "model-00002-of-00002.safetensors",
859
+ "vl_decoder.high_res_transformer1.mlp.0.weight": "model-00002-of-00002.safetensors",
860
+ "vl_decoder.high_res_transformer1.mlp.2.bias": "model-00002-of-00002.safetensors",
861
+ "vl_decoder.high_res_transformer1.mlp.2.weight": "model-00002-of-00002.safetensors",
862
+ "vl_decoder.high_res_transformer1.norm1.weight": "model-00002-of-00002.safetensors",
863
+ "vl_decoder.high_res_transformer1.norm2.weight": "model-00002-of-00002.safetensors",
864
+ "vl_decoder.high_res_transformer1.norm3.weight": "model-00002-of-00002.safetensors",
865
+ "vl_decoder.high_res_transformer1.norm4.weight": "model-00002-of-00002.safetensors",
866
+ "vl_decoder.high_res_transformer1.norm5.weight": "model-00002-of-00002.safetensors",
867
+ "vl_decoder.high_res_transformer1.norm6.weight": "model-00002-of-00002.safetensors",
868
+ "vl_decoder.high_res_transformer1.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
869
+ "vl_decoder.high_res_transformer1.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
870
+ "vl_decoder.high_res_transformer1.self_attn.proj.bias": "model-00002-of-00002.safetensors",
871
+ "vl_decoder.high_res_transformer1.self_attn.proj.weight": "model-00002-of-00002.safetensors",
872
+ "vl_decoder.high_res_transformer1.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
873
+ "vl_decoder.high_res_transformer1.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
874
+ "vl_decoder.high_res_transformer1.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
875
+ "vl_decoder.high_res_transformer1.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
876
+ "vl_decoder.high_res_transformer2.cross_attn_image_to_query.k_proj.bias": "model-00002-of-00002.safetensors",
877
+ "vl_decoder.high_res_transformer2.cross_attn_image_to_query.k_proj.weight": "model-00002-of-00002.safetensors",
878
+ "vl_decoder.high_res_transformer2.cross_attn_image_to_query.proj.bias": "model-00002-of-00002.safetensors",
879
+ "vl_decoder.high_res_transformer2.cross_attn_image_to_query.proj.weight": "model-00002-of-00002.safetensors",
880
+ "vl_decoder.high_res_transformer2.cross_attn_image_to_query.q_proj.bias": "model-00002-of-00002.safetensors",
881
+ "vl_decoder.high_res_transformer2.cross_attn_image_to_query.q_proj.weight": "model-00002-of-00002.safetensors",
882
+ "vl_decoder.high_res_transformer2.cross_attn_image_to_query.v_proj.bias": "model-00002-of-00002.safetensors",
883
+ "vl_decoder.high_res_transformer2.cross_attn_image_to_query.v_proj.weight": "model-00002-of-00002.safetensors",
884
+ "vl_decoder.high_res_transformer2.cross_attn_query_to_image.k_proj.bias": "model-00002-of-00002.safetensors",
885
+ "vl_decoder.high_res_transformer2.cross_attn_query_to_image.k_proj.weight": "model-00002-of-00002.safetensors",
886
+ "vl_decoder.high_res_transformer2.cross_attn_query_to_image.proj.bias": "model-00002-of-00002.safetensors",
887
+ "vl_decoder.high_res_transformer2.cross_attn_query_to_image.proj.weight": "model-00002-of-00002.safetensors",
888
+ "vl_decoder.high_res_transformer2.cross_attn_query_to_image.q_proj.bias": "model-00002-of-00002.safetensors",
889
+ "vl_decoder.high_res_transformer2.cross_attn_query_to_image.q_proj.weight": "model-00002-of-00002.safetensors",
890
+ "vl_decoder.high_res_transformer2.cross_attn_query_to_image.v_proj.bias": "model-00002-of-00002.safetensors",
891
+ "vl_decoder.high_res_transformer2.cross_attn_query_to_image.v_proj.weight": "model-00002-of-00002.safetensors",
892
+ "vl_decoder.high_res_transformer2.mlp.0.bias": "model-00002-of-00002.safetensors",
893
+ "vl_decoder.high_res_transformer2.mlp.0.weight": "model-00002-of-00002.safetensors",
894
+ "vl_decoder.high_res_transformer2.mlp.2.bias": "model-00002-of-00002.safetensors",
895
+ "vl_decoder.high_res_transformer2.mlp.2.weight": "model-00002-of-00002.safetensors",
896
+ "vl_decoder.high_res_transformer2.norm1.weight": "model-00002-of-00002.safetensors",
897
+ "vl_decoder.high_res_transformer2.norm2.weight": "model-00002-of-00002.safetensors",
898
+ "vl_decoder.high_res_transformer2.norm3.weight": "model-00002-of-00002.safetensors",
899
+ "vl_decoder.high_res_transformer2.norm4.weight": "model-00002-of-00002.safetensors",
900
+ "vl_decoder.high_res_transformer2.norm5.weight": "model-00002-of-00002.safetensors",
901
+ "vl_decoder.high_res_transformer2.norm6.weight": "model-00002-of-00002.safetensors",
902
+ "vl_decoder.high_res_transformer2.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
903
+ "vl_decoder.high_res_transformer2.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
904
+ "vl_decoder.high_res_transformer2.self_attn.proj.bias": "model-00002-of-00002.safetensors",
905
+ "vl_decoder.high_res_transformer2.self_attn.proj.weight": "model-00002-of-00002.safetensors",
906
+ "vl_decoder.high_res_transformer2.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
907
+ "vl_decoder.high_res_transformer2.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
908
+ "vl_decoder.high_res_transformer2.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
909
+ "vl_decoder.high_res_transformer2.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
910
+ "vl_decoder.input_projection.0.weight": "model-00002-of-00002.safetensors",
911
+ "vl_decoder.input_projection.1.bias": "model-00002-of-00002.safetensors",
912
+ "vl_decoder.input_projection.1.weight": "model-00002-of-00002.safetensors",
913
+ "vl_decoder.input_projection.3.bias": "model-00002-of-00002.safetensors",
914
+ "vl_decoder.input_projection.3.weight": "model-00002-of-00002.safetensors",
915
+ "vl_decoder.low_res_transformer.cross_attn_image_to_query.k_proj.bias": "model-00002-of-00002.safetensors",
916
+ "vl_decoder.low_res_transformer.cross_attn_image_to_query.k_proj.weight": "model-00002-of-00002.safetensors",
917
+ "vl_decoder.low_res_transformer.cross_attn_image_to_query.proj.bias": "model-00002-of-00002.safetensors",
918
+ "vl_decoder.low_res_transformer.cross_attn_image_to_query.proj.weight": "model-00002-of-00002.safetensors",
919
+ "vl_decoder.low_res_transformer.cross_attn_image_to_query.q_proj.bias": "model-00002-of-00002.safetensors",
920
+ "vl_decoder.low_res_transformer.cross_attn_image_to_query.q_proj.weight": "model-00002-of-00002.safetensors",
921
+ "vl_decoder.low_res_transformer.cross_attn_image_to_query.v_proj.bias": "model-00002-of-00002.safetensors",
922
+ "vl_decoder.low_res_transformer.cross_attn_image_to_query.v_proj.weight": "model-00002-of-00002.safetensors",
923
+ "vl_decoder.low_res_transformer.cross_attn_query_to_image.k_proj.bias": "model-00002-of-00002.safetensors",
924
+ "vl_decoder.low_res_transformer.cross_attn_query_to_image.k_proj.weight": "model-00002-of-00002.safetensors",
925
+ "vl_decoder.low_res_transformer.cross_attn_query_to_image.proj.bias": "model-00002-of-00002.safetensors",
926
+ "vl_decoder.low_res_transformer.cross_attn_query_to_image.proj.weight": "model-00002-of-00002.safetensors",
927
+ "vl_decoder.low_res_transformer.cross_attn_query_to_image.q_proj.bias": "model-00002-of-00002.safetensors",
928
+ "vl_decoder.low_res_transformer.cross_attn_query_to_image.q_proj.weight": "model-00002-of-00002.safetensors",
929
+ "vl_decoder.low_res_transformer.cross_attn_query_to_image.v_proj.bias": "model-00002-of-00002.safetensors",
930
+ "vl_decoder.low_res_transformer.cross_attn_query_to_image.v_proj.weight": "model-00002-of-00002.safetensors",
931
+ "vl_decoder.low_res_transformer.mlp.0.bias": "model-00002-of-00002.safetensors",
932
+ "vl_decoder.low_res_transformer.mlp.0.weight": "model-00002-of-00002.safetensors",
933
+ "vl_decoder.low_res_transformer.mlp.2.bias": "model-00002-of-00002.safetensors",
934
+ "vl_decoder.low_res_transformer.mlp.2.weight": "model-00002-of-00002.safetensors",
935
+ "vl_decoder.low_res_transformer.norm1.weight": "model-00002-of-00002.safetensors",
936
+ "vl_decoder.low_res_transformer.norm2.weight": "model-00002-of-00002.safetensors",
937
+ "vl_decoder.low_res_transformer.norm3.weight": "model-00002-of-00002.safetensors",
938
+ "vl_decoder.low_res_transformer.norm4.weight": "model-00002-of-00002.safetensors",
939
+ "vl_decoder.low_res_transformer.norm5.weight": "model-00002-of-00002.safetensors",
940
+ "vl_decoder.low_res_transformer.norm6.weight": "model-00002-of-00002.safetensors",
941
+ "vl_decoder.low_res_transformer.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
942
+ "vl_decoder.low_res_transformer.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
943
+ "vl_decoder.low_res_transformer.self_attn.proj.bias": "model-00002-of-00002.safetensors",
944
+ "vl_decoder.low_res_transformer.self_attn.proj.weight": "model-00002-of-00002.safetensors",
945
+ "vl_decoder.low_res_transformer.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
946
+ "vl_decoder.low_res_transformer.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
947
+ "vl_decoder.low_res_transformer.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
948
+ "vl_decoder.low_res_transformer.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
949
+ "vl_decoder.mask_output_mlp.0.bias": "model-00002-of-00002.safetensors",
950
+ "vl_decoder.mask_output_mlp.0.weight": "model-00002-of-00002.safetensors",
951
+ "vl_decoder.mask_output_mlp.2.bias": "model-00002-of-00002.safetensors",
952
+ "vl_decoder.mask_output_mlp.2.weight": "model-00002-of-00002.safetensors",
953
+ "vl_decoder.mask_output_mlp.4.bias": "model-00002-of-00002.safetensors",
954
+ "vl_decoder.mask_output_mlp.4.weight": "model-00002-of-00002.safetensors",
955
+ "vl_decoder.mask_output_upscaling1.0.bias": "model-00002-of-00002.safetensors",
956
+ "vl_decoder.mask_output_upscaling1.0.weight": "model-00002-of-00002.safetensors",
957
+ "vl_decoder.mask_output_upscaling1.1.weight": "model-00002-of-00002.safetensors",
958
+ "vl_decoder.mask_output_upscaling2.0.bias": "model-00002-of-00002.safetensors",
959
+ "vl_decoder.mask_output_upscaling2.0.weight": "model-00002-of-00002.safetensors",
960
+ "vl_decoder.score_prediction.bias": "model-00002-of-00002.safetensors",
961
+ "vl_decoder.score_prediction.weight": "model-00002-of-00002.safetensors",
962
+ "vl_decoder.vp_embedding.weight": "model-00002-of-00002.safetensors"
963
+ }
964
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 12845056,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 12845056,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
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:b5c1be09b1106e73ad7d22b9a606d9dbac5d8472eab42e9e0b07ae5806dc0481
3
+ size 11474902
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 131072,
204
+ "pad_token": "<|endoftext|>",
205
+ "processor_class": "Qwen2_5_VLProcessor",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null
209
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2991d6be67dc019e07ecfba7898c46e392c0da1380aed29b2c79c2292ab086e1
3
+ size 8824
vocab.json ADDED
The diff for this file is too large to render. See raw diff