Hugging Face's logo

inclusionAI
/
M2-Reasoning

Safetensors
bailing_qwen2_5
Model card Files Community
LandyGuo commited on
Commit
8773391
·
1 Parent(s): 45b78a4

upload model

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +60 -0
  3. chat_template.json +3 -0
  4. config.json +233 -0
  5. generation_config.json +4 -0
  6. merges.txt +0 -0
  7. model-00001-of-00004.safetensors +3 -0
  8. model-00002-of-00004.safetensors +3 -0
  9. model-00003-of-00004.safetensors +3 -0
  10. model-00004-of-00004.safetensors +3 -0
  11. model.safetensors.index.json +740 -0
  12. preprocessor_config.json +29 -0
  13. special_tokens_map.json +35 -0
  14. tokenizer.json +3 -0
  15. tokenizer_config.json +501 -0
  16. 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 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</answer>": 151679,
3
+ "</audio>": 151695,
4
+ "</body>": 151669,
5
+ "</gen_audio>": 151698,
6
+ "</gen_image>": 151689,
7
+ "</html>": 151667,
8
+ "</image>": 151684,
9
+ "</table>": 151671,
10
+ "</td>": 151675,
11
+ "</think>": 151677,
12
+ "</tool_call>": 151658,
13
+ "</tr>": 151673,
14
+ "</video>": 151686,
15
+ "<answer>": 151678,
16
+ "<audio>": 151694,
17
+ "<audioHere>": 151699,
18
+ "<audioPatch>": 151693,
19
+ "<body>": 151668,
20
+ "<end_of_audio>": 151692,
21
+ "<end_of_chunk>": 151691,
22
+ "<framePatch>": 151700,
23
+ "<gen_audio>": 151697,
24
+ "<gen_audioPatch>": 151696,
25
+ "<gen_image>": 151688,
26
+ "<gen_imagePatch>": 151687,
27
+ "<html>": 151666,
28
+ "<image>": 151683,
29
+ "<imageHere>": 151690,
30
+ "<imagePatch>": 151682,
31
+ "<table>": 151670,
32
+ "<td>": 151674,
33
+ "<think>": 151676,
34
+ "<tool_call>": 151657,
35
+ "<tr>": 151672,
36
+ "<video>": 151685,
37
+ "<|box_end|>": 151649,
38
+ "<|box_start|>": 151648,
39
+ "<|endoftext|>": 151643,
40
+ "<|file_sep|>": 151664,
41
+ "<|fim_middle|>": 151660,
42
+ "<|fim_pad|>": 151662,
43
+ "<|fim_prefix|>": 151659,
44
+ "<|fim_suffix|>": 151661,
45
+ "<|im_end|>": 151645,
46
+ "<|im_start|>": 151644,
47
+ "<|image_pad|>": 151655,
48
+ "<|object_ref_end|>": 151647,
49
+ "<|object_ref_start|>": 151646,
50
+ "<|quad_end|>": 151651,
51
+ "<|quad_start|>": 151650,
52
+ "<|repo_name|>": 151663,
53
+ "<|startoftext|>": 151680,
54
+ "<|video_pad|>": 151656,
55
+ "<|vision_end|>": 151653,
56
+ "<|vision_pad|>": 151654,
57
+ "<|vision_start|>": 151652,
58
+ "[gMASK]": 151681,
59
+ "[item]": 151665
60
+ }
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 +1,233 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Bailing_qwen2_5NativeForConditionalGeneration"
4
+ ],
5
+ "audio_config": null,
6
+ "llm_config": {
7
+ "_attn_implementation_autoset": false,
8
+ "_name_or_path": "/video_hy2/workspace/rulixiang.rlx/transformers-4.49.0/saved_glm_model/",
9
+ "add_cross_attention": false,
10
+ "architectures": [
11
+ "Qwen2ForCausalLM"
12
+ ],
13
+ "attention_dropout": 0.0,
14
+ "audio_end_token": 151695,
15
+ "audio_id_shift": 151701,
16
+ "audio_patch_token": 151693,
17
+ "audio_start_token": 151694,
18
+ "audio_vocab_size": 4099,
19
+ "bad_words_ids": null,
20
+ "begin_suppress_tokens": null,
21
+ "bos_token_id": null,
22
+ "chunk_size_feed_forward": 0,
23
+ "cross_attention_hidden_size": null,
24
+ "decoder_start_token_id": null,
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "early_stopping": false,
28
+ "encoder_no_repeat_ngram_size": 0,
29
+ "end_of_audio_token": 151692,
30
+ "end_of_chunk_token": 151691,
31
+ "eos_token_id": 151645,
32
+ "exponential_decay_length_penalty": null,
33
+ "finetuning_task": null,
34
+ "first_signal_token": null,
35
+ "forced_bos_token_id": null,
36
+ "forced_eos_token_id": null,
37
+ "frame_patch_token": 151700,
38
+ "gen_audio_end_token": 151698,
39
+ "gen_audio_patch_token": 151696,
40
+ "gen_audio_start_token": 151697,
41
+ "gen_image_end_token": 151689,
42
+ "gen_image_patch_token": 151687,
43
+ "gen_image_start_token": 151688,
44
+ "hidden_act": "silu",
45
+ "hidden_size": 3584,
46
+ "id2label": {
47
+ "0": "LABEL_0",
48
+ "1": "LABEL_1"
49
+ },
50
+ "image_end_token": 151684,
51
+ "image_patch_token": 151682,
52
+ "image_start_token": 151683,
53
+ "image_token_id": 151682,
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 18944,
56
+ "is_decoder": false,
57
+ "is_encoder_decoder": false,
58
+ "label2id": {
59
+ "LABEL_0": 0,
60
+ "LABEL_1": 1
61
+ },
62
+ "length_penalty": 1.0,
63
+ "max_length": 20,
64
+ "max_position_embeddings": 32768,
65
+ "max_window_layers": 28,
66
+ "min_length": 0,
67
+ "model_type": "qwen2",
68
+ "no_repeat_ngram_size": 0,
69
+ "num_attention_heads": 28,
70
+ "num_audio_token": 256,
71
+ "num_beam_groups": 1,
72
+ "num_beams": 1,
73
+ "num_decoder_audio_token": 512,
74
+ "num_decoder_image_token": 1024,
75
+ "num_hidden_layers": 28,
76
+ "num_image_token": 1280,
77
+ "num_key_value_heads": 4,
78
+ "num_return_sequences": 1,
79
+ "num_video_token": 5120,
80
+ "output_attentions": false,
81
+ "output_hidden_states": false,
82
+ "output_scores": false,
83
+ "pad_token_id": null,
84
+ "placeholder_audio_token_in_text": 151699,
85
+ "placeholder_image_token_in_text": 151690,
86
+ "prefix": null,
87
+ "problem_type": null,
88
+ "pruned_heads": {},
89
+ "remove_invalid_values": false,
90
+ "repetition_penalty": 1.0,
91
+ "return_dict": true,
92
+ "return_dict_in_generate": false,
93
+ "rms_norm_eps": 1e-06,
94
+ "rope_scaling": {
95
+ "mrope_section": [
96
+ 16,
97
+ 24,
98
+ 24
99
+ ],
100
+ "rope_type": "default",
101
+ "type": "default"
102
+ },
103
+ "rope_theta": 1000000.0,
104
+ "sep_token_id": null,
105
+ "sliding_window": 131072,
106
+ "spatial_merge_size": 2,
107
+ "suppress_tokens": null,
108
+ "task_specific_params": null,
109
+ "temperature": 1.0,
110
+ "tf_legacy_loss": false,
111
+ "tie_encoder_decoder": false,
112
+ "tie_word_embeddings": false,
113
+ "tokenizer_class": null,
114
+ "tokens_per_second": 2,
115
+ "top_k": 50,
116
+ "top_p": 1.0,
117
+ "torch_dtype": "bfloat16",
118
+ "torchscript": false,
119
+ "typical_p": 1.0,
120
+ "use_bfloat16": false,
121
+ "use_cache": true,
122
+ "use_llm_3drope": "m_rope",
123
+ "use_sliding_window": false,
124
+ "video_end_token": 151686,
125
+ "video_patch_token": 151682,
126
+ "video_start_token": 151685,
127
+ "vocab_size": 152064
128
+ },
129
+ "llm_type": "qwen2_5",
130
+ "mlp_depths": 2,
131
+ "model_type": "bailing_qwen2_5",
132
+ "num_decoder_audio_token": 512,
133
+ "num_decoder_image_token": 1024,
134
+ "num_query_token_audio": 256,
135
+ "num_query_token_image": 64,
136
+ "num_query_token_video": 64,
137
+ "select_layer": -1,
138
+ "torch_dtype": "bfloat16",
139
+ "transformers_version": "4.49.0",
140
+ "use_llm_lora": 0,
141
+ "use_vit_lora": 0,
142
+ "vision_config": {
143
+ "_attn_implementation_autoset": true,
144
+ "_name_or_path": "/video_hy2/workspace/rulixiang.rlx/transformers-4.49.0/saved_vision_model/",
145
+ "add_cross_attention": false,
146
+ "architectures": [
147
+ "Qwen2_5_VisionTransformer"
148
+ ],
149
+ "auto_map": {
150
+ "AutoConfig": "configuration_qwen2_5_vit.Qwen2_5_VLVisionConfig",
151
+ "AutoModel": "qwen2_5_vit.Qwen2_5_VisionTransformer"
152
+ },
153
+ "bad_words_ids": null,
154
+ "begin_suppress_tokens": null,
155
+ "bos_token_id": null,
156
+ "chunk_size_feed_forward": 0,
157
+ "cross_attention_hidden_size": null,
158
+ "decoder_start_token_id": null,
159
+ "depth": 32,
160
+ "diversity_penalty": 0.0,
161
+ "do_sample": false,
162
+ "early_stopping": false,
163
+ "encoder_no_repeat_ngram_size": 0,
164
+ "eos_token_id": null,
165
+ "exponential_decay_length_penalty": null,
166
+ "finetuning_task": null,
167
+ "forced_bos_token_id": null,
168
+ "forced_eos_token_id": null,
169
+ "fullatt_block_indexes": [
170
+ 7,
171
+ 15,
172
+ 23,
173
+ 31
174
+ ],
175
+ "hidden_act": "silu",
176
+ "hidden_size": 1280,
177
+ "id2label": {
178
+ "0": "LABEL_0",
179
+ "1": "LABEL_1"
180
+ },
181
+ "in_channels": 3,
182
+ "in_chans": 3,
183
+ "intermediate_size": 3456,
184
+ "is_decoder": false,
185
+ "is_encoder_decoder": false,
186
+ "label2id": {
187
+ "LABEL_0": 0,
188
+ "LABEL_1": 1
189
+ },
190
+ "length_penalty": 1.0,
191
+ "max_length": 20,
192
+ "min_length": 0,
193
+ "model_type": "qwen2_5_vit",
194
+ "no_repeat_ngram_size": 0,
195
+ "num_beam_groups": 1,
196
+ "num_beams": 1,
197
+ "num_heads": 16,
198
+ "num_return_sequences": 1,
199
+ "out_hidden_size": 8192,
200
+ "output_attentions": false,
201
+ "output_hidden_states": false,
202
+ "output_scores": false,
203
+ "pad_token_id": null,
204
+ "patch_size": 14,
205
+ "prefix": null,
206
+ "problem_type": null,
207
+ "pruned_heads": {},
208
+ "remove_invalid_values": false,
209
+ "repetition_penalty": 1.0,
210
+ "return_dict": true,
211
+ "return_dict_in_generate": false,
212
+ "sep_token_id": null,
213
+ "spatial_merge_size": 2,
214
+ "spatial_patch_size": 14,
215
+ "suppress_tokens": null,
216
+ "task_specific_params": null,
217
+ "temperature": 1.0,
218
+ "temporal_patch_size": 2,
219
+ "tf_legacy_loss": false,
220
+ "tie_encoder_decoder": false,
221
+ "tie_word_embeddings": true,
222
+ "tokenizer_class": null,
223
+ "tokens_per_second": 2,
224
+ "top_k": 50,
225
+ "top_p": 1.0,
226
+ "torch_dtype": "bfloat16",
227
+ "torchscript": false,
228
+ "typical_p": 1.0,
229
+ "use_bfloat16": false,
230
+ "window_size": 112
231
+ },
232
+ "vision_type": "qwen2_5_vit"
233
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.49.0"
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8851f1dd1882755d817766bf7aaa2eeaf7d106830075bec06e3af07cc4d852da
3
+ size 4888503056
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d8c629212dc05b35c777a87fa771684fae1cc57587f7e7299169f6dad7d1ee4
3
+ size 4932752808
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:435fafd26308070546e2c98a1fa21b7bf0787f5038d1d56e743e0201e7c4897f
3
+ size 4991497848
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2515e87863a7406a6b3c7e9b91a93dfc2fdf52f5e7921465978b47d32ef9c18
3
+ size 1912140440
model.safetensors.index.json ADDED
@@ -0,0 +1,740 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16724805120
4
+ },
5
+ "weight_map": {
6
+ "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "language_model.model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
93
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
94
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
97
+ "language_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "language_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
105
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
106
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
107
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
108
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
109
+ "language_model.model.layers.16.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
110
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
111
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
112
+ "language_model.model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
113
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
114
+ "language_model.model.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
115
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
116
+ "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
117
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
118
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
119
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
120
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
121
+ "language_model.model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
122
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
123
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
124
+ "language_model.model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
125
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
126
+ "language_model.model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
127
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
128
+ "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
132
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
134
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
135
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "language_model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "language_model.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "language_model.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "language_model.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "language_model.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "language_model.model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
237
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
238
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
240
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
241
+ "language_model.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "language_model.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "language_model.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
249
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
250
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
251
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
252
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
253
+ "language_model.model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
254
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
255
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
256
+ "language_model.model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
257
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
258
+ "language_model.model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
259
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
260
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
285
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
286
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
287
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
288
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
289
+ "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
297
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
298
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
299
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
300
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
301
+ "language_model.model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
302
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
303
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
304
+ "language_model.model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
305
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
306
+ "language_model.model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
307
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
308
+ "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
309
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
310
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
311
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
312
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
313
+ "language_model.model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
314
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
315
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
316
+ "language_model.model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
317
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
318
+ "language_model.model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
319
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
320
+ "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
326
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
327
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
328
+ "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
329
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
330
+ "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
331
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
332
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
345
+ "linear_proj.0.bias": "model-00004-of-00004.safetensors",
346
+ "linear_proj.0.weight": "model-00004-of-00004.safetensors",
347
+ "linear_proj.2.bias": "model-00004-of-00004.safetensors",
348
+ "linear_proj.2.weight": "model-00004-of-00004.safetensors",
349
+ "vision_model.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
350
+ "vision_model.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
351
+ "vision_model.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
352
+ "vision_model.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
353
+ "vision_model.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
354
+ "vision_model.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
355
+ "vision_model.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
356
+ "vision_model.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
357
+ "vision_model.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
358
+ "vision_model.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
359
+ "vision_model.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
360
+ "vision_model.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
361
+ "vision_model.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
362
+ "vision_model.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
363
+ "vision_model.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
364
+ "vision_model.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
365
+ "vision_model.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
366
+ "vision_model.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
367
+ "vision_model.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
368
+ "vision_model.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
369
+ "vision_model.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
370
+ "vision_model.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
371
+ "vision_model.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
372
+ "vision_model.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
373
+ "vision_model.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
374
+ "vision_model.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
375
+ "vision_model.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
376
+ "vision_model.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
377
+ "vision_model.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
378
+ "vision_model.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
379
+ "vision_model.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
380
+ "vision_model.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
381
+ "vision_model.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
382
+ "vision_model.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
383
+ "vision_model.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
384
+ "vision_model.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
385
+ "vision_model.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
386
+ "vision_model.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
387
+ "vision_model.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
388
+ "vision_model.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
389
+ "vision_model.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
390
+ "vision_model.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
391
+ "vision_model.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
392
+ "vision_model.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
393
+ "vision_model.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
394
+ "vision_model.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
395
+ "vision_model.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
396
+ "vision_model.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
397
+ "vision_model.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
398
+ "vision_model.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
399
+ "vision_model.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
400
+ "vision_model.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
401
+ "vision_model.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
402
+ "vision_model.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
403
+ "vision_model.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
404
+ "vision_model.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
405
+ "vision_model.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
406
+ "vision_model.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
407
+ "vision_model.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
408
+ "vision_model.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
409
+ "vision_model.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
410
+ "vision_model.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
411
+ "vision_model.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
412
+ "vision_model.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
413
+ "vision_model.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
414
+ "vision_model.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
415
+ "vision_model.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
416
+ "vision_model.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
417
+ "vision_model.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
418
+ "vision_model.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
419
+ "vision_model.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
420
+ "vision_model.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
421
+ "vision_model.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
422
+ "vision_model.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
423
+ "vision_model.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
424
+ "vision_model.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
425
+ "vision_model.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
426
+ "vision_model.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
427
+ "vision_model.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
428
+ "vision_model.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
429
+ "vision_model.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
430
+ "vision_model.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
431
+ "vision_model.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
432
+ "vision_model.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
433
+ "vision_model.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
434
+ "vision_model.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
435
+ "vision_model.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
436
+ "vision_model.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
437
+ "vision_model.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
438
+ "vision_model.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
439
+ "vision_model.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
440
+ "vision_model.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
441
+ "vision_model.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
442
+ "vision_model.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
443
+ "vision_model.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
444
+ "vision_model.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
445
+ "vision_model.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
446
+ "vision_model.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
447
+ "vision_model.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
448
+ "vision_model.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
449
+ "vision_model.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
450
+ "vision_model.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
451
+ "vision_model.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
452
+ "vision_model.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
453
+ "vision_model.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
454
+ "vision_model.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
455
+ "vision_model.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
456
+ "vision_model.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
457
+ "vision_model.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
458
+ "vision_model.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
459
+ "vision_model.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
460
+ "vision_model.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
461
+ "vision_model.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
462
+ "vision_model.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
463
+ "vision_model.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
464
+ "vision_model.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
465
+ "vision_model.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
466
+ "vision_model.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
467
+ "vision_model.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
468
+ "vision_model.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
469
+ "vision_model.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
470
+ "vision_model.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
471
+ "vision_model.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
472
+ "vision_model.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
473
+ "vision_model.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
474
+ "vision_model.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
475
+ "vision_model.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
476
+ "vision_model.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
477
+ "vision_model.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
478
+ "vision_model.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
479
+ "vision_model.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
480
+ "vision_model.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
481
+ "vision_model.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
482
+ "vision_model.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
483
+ "vision_model.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
484
+ "vision_model.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
485
+ "vision_model.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
486
+ "vision_model.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
487
+ "vision_model.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
488
+ "vision_model.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
489
+ "vision_model.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
490
+ "vision_model.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
491
+ "vision_model.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
492
+ "vision_model.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
493
+ "vision_model.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
494
+ "vision_model.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
495
+ "vision_model.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
496
+ "vision_model.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
497
+ "vision_model.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
498
+ "vision_model.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
499
+ "vision_model.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
500
+ "vision_model.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
501
+ "vision_model.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
502
+ "vision_model.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
503
+ "vision_model.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
504
+ "vision_model.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
505
+ "vision_model.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
506
+ "vision_model.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
507
+ "vision_model.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
508
+ "vision_model.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
509
+ "vision_model.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
510
+ "vision_model.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
511
+ "vision_model.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
512
+ "vision_model.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
513
+ "vision_model.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
514
+ "vision_model.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
515
+ "vision_model.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
516
+ "vision_model.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
517
+ "vision_model.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
518
+ "vision_model.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
519
+ "vision_model.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
520
+ "vision_model.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
521
+ "vision_model.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
522
+ "vision_model.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
523
+ "vision_model.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
524
+ "vision_model.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
525
+ "vision_model.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
526
+ "vision_model.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
527
+ "vision_model.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
528
+ "vision_model.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
529
+ "vision_model.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
530
+ "vision_model.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
531
+ "vision_model.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
532
+ "vision_model.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
533
+ "vision_model.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
534
+ "vision_model.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
535
+ "vision_model.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
536
+ "vision_model.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
537
+ "vision_model.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
538
+ "vision_model.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
539
+ "vision_model.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
540
+ "vision_model.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
541
+ "vision_model.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
542
+ "vision_model.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
543
+ "vision_model.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
544
+ "vision_model.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
545
+ "vision_model.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
546
+ "vision_model.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
547
+ "vision_model.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
548
+ "vision_model.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
549
+ "vision_model.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
550
+ "vision_model.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
551
+ "vision_model.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
552
+ "vision_model.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
553
+ "vision_model.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
554
+ "vision_model.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
555
+ "vision_model.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
556
+ "vision_model.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
557
+ "vision_model.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
558
+ "vision_model.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
559
+ "vision_model.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
560
+ "vision_model.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
561
+ "vision_model.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
562
+ "vision_model.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
563
+ "vision_model.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
564
+ "vision_model.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
565
+ "vision_model.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
566
+ "vision_model.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
567
+ "vision_model.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
568
+ "vision_model.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
569
+ "vision_model.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
570
+ "vision_model.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
571
+ "vision_model.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
572
+ "vision_model.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
573
+ "vision_model.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
574
+ "vision_model.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
575
+ "vision_model.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
576
+ "vision_model.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
577
+ "vision_model.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
578
+ "vision_model.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
579
+ "vision_model.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
580
+ "vision_model.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
581
+ "vision_model.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
582
+ "vision_model.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
583
+ "vision_model.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
584
+ "vision_model.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
585
+ "vision_model.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
586
+ "vision_model.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
587
+ "vision_model.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
588
+ "vision_model.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
589
+ "vision_model.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
590
+ "vision_model.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
591
+ "vision_model.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
592
+ "vision_model.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
593
+ "vision_model.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
594
+ "vision_model.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
595
+ "vision_model.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
596
+ "vision_model.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
597
+ "vision_model.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
598
+ "vision_model.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
599
+ "vision_model.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
600
+ "vision_model.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
601
+ "vision_model.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
602
+ "vision_model.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
603
+ "vision_model.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
604
+ "vision_model.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
605
+ "vision_model.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
606
+ "vision_model.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
607
+ "vision_model.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
608
+ "vision_model.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
609
+ "vision_model.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
610
+ "vision_model.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
611
+ "vision_model.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
612
+ "vision_model.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
613
+ "vision_model.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
614
+ "vision_model.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
615
+ "vision_model.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
616
+ "vision_model.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
617
+ "vision_model.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
618
+ "vision_model.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
619
+ "vision_model.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
620
+ "vision_model.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
621
+ "vision_model.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
622
+ "vision_model.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
623
+ "vision_model.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
624
+ "vision_model.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
625
+ "vision_model.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
626
+ "vision_model.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
627
+ "vision_model.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
628
+ "vision_model.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
629
+ "vision_model.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
630
+ "vision_model.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
631
+ "vision_model.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
632
+ "vision_model.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
633
+ "vision_model.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
634
+ "vision_model.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
635
+ "vision_model.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
636
+ "vision_model.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
637
+ "vision_model.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
638
+ "vision_model.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
639
+ "vision_model.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
640
+ "vision_model.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
641
+ "vision_model.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
642
+ "vision_model.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
643
+ "vision_model.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
644
+ "vision_model.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
645
+ "vision_model.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
646
+ "vision_model.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
647
+ "vision_model.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
648
+ "vision_model.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
649
+ "vision_model.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
650
+ "vision_model.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
651
+ "vision_model.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
652
+ "vision_model.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
653
+ "vision_model.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
654
+ "vision_model.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
655
+ "vision_model.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
656
+ "vision_model.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
657
+ "vision_model.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
658
+ "vision_model.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
659
+ "vision_model.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
660
+ "vision_model.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
661
+ "vision_model.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
662
+ "vision_model.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
663
+ "vision_model.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
664
+ "vision_model.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
665
+ "vision_model.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
666
+ "vision_model.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
667
+ "vision_model.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
668
+ "vision_model.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
669
+ "vision_model.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
670
+ "vision_model.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
671
+ "vision_model.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
672
+ "vision_model.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
673
+ "vision_model.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
674
+ "vision_model.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
675
+ "vision_model.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
676
+ "vision_model.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
677
+ "vision_model.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
678
+ "vision_model.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
679
+ "vision_model.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
680
+ "vision_model.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
681
+ "vision_model.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
682
+ "vision_model.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
683
+ "vision_model.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
684
+ "vision_model.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
685
+ "vision_model.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
686
+ "vision_model.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
687
+ "vision_model.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
688
+ "vision_model.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
689
+ "vision_model.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
690
+ "vision_model.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
691
+ "vision_model.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
692
+ "vision_model.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
693
+ "vision_model.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
694
+ "vision_model.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
695
+ "vision_model.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
696
+ "vision_model.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
697
+ "vision_model.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
698
+ "vision_model.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
699
+ "vision_model.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
700
+ "vision_model.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
701
+ "vision_model.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
702
+ "vision_model.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
703
+ "vision_model.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
704
+ "vision_model.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
705
+ "vision_model.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
706
+ "vision_model.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
707
+ "vision_model.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
708
+ "vision_model.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
709
+ "vision_model.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
710
+ "vision_model.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
711
+ "vision_model.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
712
+ "vision_model.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
713
+ "vision_model.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
714
+ "vision_model.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
715
+ "vision_model.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
716
+ "vision_model.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
717
+ "vision_model.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
718
+ "vision_model.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
719
+ "vision_model.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
720
+ "vision_model.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
721
+ "vision_model.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
722
+ "vision_model.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
723
+ "vision_model.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
724
+ "vision_model.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
725
+ "vision_model.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
726
+ "vision_model.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
727
+ "vision_model.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
728
+ "vision_model.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
729
+ "vision_model.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
730
+ "vision_model.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
731
+ "vision_model.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
732
+ "vision_model.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
733
+ "vision_model.merger.ln_q.weight": "model-00001-of-00004.safetensors",
734
+ "vision_model.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
735
+ "vision_model.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
736
+ "vision_model.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
737
+ "vision_model.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
738
+ "vision_model.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
739
+ }
740
+ }
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": "Bailing_qwen2_5Processor",
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 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "[item]",
4
+ "<html>",
5
+ "</html>",
6
+ "<body>",
7
+ "</body>",
8
+ "<table>",
9
+ "</table>",
10
+ "<tr>",
11
+ "</tr>",
12
+ "<td>",
13
+ "</td>",
14
+ "<think>",
15
+ "</think>",
16
+ "<answer>",
17
+ "</answer>",
18
+ "<|startoftext|>",
19
+ "[gMASK]"
20
+ ],
21
+ "eos_token": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "pad_token": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ }
35
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074011e23b482c4009f7e061e182085fe79b6514fe10192b54f64cbc900a8708
3
+ size 11428596
tokenizer_config.json ADDED
@@ -0,0 +1,501 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "[item]",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<html>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "</html>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<body>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "</body>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<table>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "</table>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<tr>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "</tr>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<td>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "</td>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151676": {
270
+ "content": "<think>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "</think>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151678": {
286
+ "content": "<answer>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151679": {
294
+ "content": "</answer>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151680": {
302
+ "content": "<|startoftext|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151681": {
310
+ "content": "[gMASK]",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151682": {
318
+ "content": "<imagePatch>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151683": {
326
+ "content": "<image>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151684": {
334
+ "content": "</image>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151685": {
342
+ "content": "<video>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151686": {
350
+ "content": "</video>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151687": {
358
+ "content": "<gen_imagePatch>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151688": {
366
+ "content": "<gen_image>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151689": {
374
+ "content": "</gen_image>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151690": {
382
+ "content": "<imageHere>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151691": {
390
+ "content": "<end_of_chunk>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151692": {
398
+ "content": "<end_of_audio>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151693": {
406
+ "content": "<audioPatch>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151694": {
414
+ "content": "<audio>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151695": {
422
+ "content": "</audio>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151696": {
430
+ "content": "<gen_audioPatch>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151697": {
438
+ "content": "<gen_audio>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151698": {
446
+ "content": "</gen_audio>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151699": {
454
+ "content": "<audioHere>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151700": {
462
+ "content": "<framePatch>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ }
469
+ },
470
+ "additional_special_tokens": [
471
+ "[item]",
472
+ "<html>",
473
+ "</html>",
474
+ "<body>",
475
+ "</body>",
476
+ "<table>",
477
+ "</table>",
478
+ "<tr>",
479
+ "</tr>",
480
+ "<td>",
481
+ "</td>",
482
+ "<think>",
483
+ "</think>",
484
+ "<answer>",
485
+ "</answer>",
486
+ "<|startoftext|>",
487
+ "[gMASK]"
488
+ ],
489
+ "bos_token": "<|im_start|>",
490
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
491
+ "clean_up_tokenization_spaces": false,
492
+ "eos_token": "<|im_end|>",
493
+ "errors": "replace",
494
+ "extra_special_tokens": {},
495
+ "model_max_length": 131072,
496
+ "pad_token": "<|endoftext|>",
497
+ "processor_class": "Qwen2VLProcessor",
498
+ "split_special_tokens": false,
499
+ "tokenizer_class": "Qwen2Tokenizer",
500
+ "unk_token": null
501
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff