Hugging Face's logo

mlx-community
/
colnomic-embed-multimodal-3b-4bit

Safetensors
colqwen2_5
Model card Files
xet
Community
1
qnguyen3 commited on
Commit
5c455e4
·
verified ·
1 Parent(s): 6840a74

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. chat_template.jinja +54 -0
  4. config copy.json +65 -0
  5. config.json +231 -0
  6. generation_config.json +15 -0
  7. merges.txt +0 -0
  8. model.safetensors +3 -0
  9. model.safetensors.index.json +833 -0
  10. preprocessor_config.json +31 -0
  11. special_tokens_map.json +31 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +208 -0
  14. 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 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\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>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\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" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
config copy.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ColQwen2_5"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 2048,
10
+ "image_token_id": 151655,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 128000,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2_5_vl",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 36,
18
+ "num_key_value_heads": 2,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": {
21
+ "mrope_section": [
22
+ 16,
23
+ 24,
24
+ 24
25
+ ],
26
+ "rope_type": "default",
27
+ "type": "default"
28
+ },
29
+ "rope_theta": 1000000.0,
30
+ "sliding_window": 32768,
31
+ "tie_word_embeddings": true,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.51.3",
34
+ "use_cache": true,
35
+ "use_sliding_window": false,
36
+ "video_token_id": 151656,
37
+ "vision_config": {
38
+ "depth": 32,
39
+ "fullatt_block_indexes": [
40
+ 7,
41
+ 15,
42
+ 23,
43
+ 31
44
+ ],
45
+ "hidden_act": "silu",
46
+ "hidden_size": 1280,
47
+ "in_channels": 3,
48
+ "in_chans": 3,
49
+ "intermediate_size": 3420,
50
+ "model_type": "qwen2_5_vl",
51
+ "num_heads": 16,
52
+ "out_hidden_size": 2048,
53
+ "patch_size": 14,
54
+ "spatial_merge_size": 2,
55
+ "spatial_patch_size": 14,
56
+ "temporal_patch_size": 2,
57
+ "tokens_per_second": 2,
58
+ "torch_dtype": "bfloat16",
59
+ "window_size": 112
60
+ },
61
+ "vision_end_token_id": 151653,
62
+ "vision_start_token_id": 151652,
63
+ "vision_token_id": 151654,
64
+ "vocab_size": 151936
65
+ }
config.json ADDED
@@ -0,0 +1,231 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ColQwen2_5ForRetrieval"
4
+ ],
5
+ "embedding_dim": 128,
6
+ "initializer_range": 0.02,
7
+ "is_composition": false,
8
+ "model_type": "colqwen2_5",
9
+ "quantization": {
10
+ "group_size": 64,
11
+ "bits": 4
12
+ },
13
+ "torch_dtype": "bfloat16",
14
+ "transformers_version": "4.53.0.dev0",
15
+ "vlm_config": {
16
+ "_name_or_path": "Qwen/Qwen2_5-VL-3B-Instruct",
17
+ "attention_dropout": 0.0,
18
+ "bos_token_id": 151643,
19
+ "eos_token_id": 151645,
20
+ "hidden_act": "silu",
21
+ "hidden_size": 2048,
22
+ "image_token_id": 151655,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 11008,
25
+ "max_position_embeddings": 128000,
26
+ "max_window_layers": 70,
27
+ "model_type": "qwen2_5_vl",
28
+ "num_attention_heads": 16,
29
+ "num_hidden_layers": 36,
30
+ "num_key_value_heads": 2,
31
+ "rms_norm_eps": 1e-06,
32
+ "rope_scaling": {
33
+ "mrope_section": [
34
+ 16,
35
+ 24,
36
+ 24
37
+ ],
38
+ "rope_type": "default",
39
+ "type": "default"
40
+ },
41
+ "rope_theta": 1000000.0,
42
+ "sliding_window": 32768,
43
+ "text_config": {
44
+ "_name_or_path": "",
45
+ "add_cross_attention": false,
46
+ "architectures": [
47
+ "ColQwen2_5"
48
+ ],
49
+ "attention_dropout": 0.0,
50
+ "bad_words_ids": null,
51
+ "begin_suppress_tokens": null,
52
+ "bos_token_id": 151643,
53
+ "chunk_size_feed_forward": 0,
54
+ "cross_attention_hidden_size": null,
55
+ "decoder_start_token_id": null,
56
+ "diversity_penalty": 0.0,
57
+ "do_sample": false,
58
+ "early_stopping": false,
59
+ "encoder_no_repeat_ngram_size": 0,
60
+ "eos_token_id": 151645,
61
+ "exponential_decay_length_penalty": null,
62
+ "finetuning_task": null,
63
+ "forced_bos_token_id": null,
64
+ "forced_eos_token_id": null,
65
+ "hidden_act": "silu",
66
+ "hidden_size": 2048,
67
+ "id2label": {
68
+ "0": "LABEL_0",
69
+ "1": "LABEL_1"
70
+ },
71
+ "image_token_id": null,
72
+ "initializer_range": 0.02,
73
+ "intermediate_size": 11008,
74
+ "is_decoder": false,
75
+ "is_encoder_decoder": false,
76
+ "label2id": {
77
+ "LABEL_0": 0,
78
+ "LABEL_1": 1
79
+ },
80
+ "length_penalty": 1.0,
81
+ "max_length": 20,
82
+ "max_position_embeddings": 128000,
83
+ "max_window_layers": 70,
84
+ "min_length": 0,
85
+ "model_type": "qwen2_5_vl_text",
86
+ "no_repeat_ngram_size": 0,
87
+ "num_attention_heads": 16,
88
+ "num_beam_groups": 1,
89
+ "num_beams": 1,
90
+ "num_hidden_layers": 36,
91
+ "num_key_value_heads": 2,
92
+ "num_return_sequences": 1,
93
+ "output_attentions": false,
94
+ "output_hidden_states": false,
95
+ "output_scores": false,
96
+ "pad_token_id": null,
97
+ "prefix": null,
98
+ "problem_type": null,
99
+ "pruned_heads": {},
100
+ "remove_invalid_values": false,
101
+ "repetition_penalty": 1.0,
102
+ "return_dict": true,
103
+ "return_dict_in_generate": false,
104
+ "rms_norm_eps": 1e-06,
105
+ "rope_scaling": {
106
+ "mrope_section": [
107
+ 16,
108
+ 24,
109
+ 24
110
+ ],
111
+ "rope_type": "default",
112
+ "type": "default"
113
+ },
114
+ "rope_theta": 1000000.0,
115
+ "sep_token_id": null,
116
+ "sliding_window": 32768,
117
+ "suppress_tokens": null,
118
+ "task_specific_params": null,
119
+ "temperature": 1.0,
120
+ "tf_legacy_loss": false,
121
+ "tie_encoder_decoder": false,
122
+ "tie_word_embeddings": true,
123
+ "tokenizer_class": null,
124
+ "top_k": 50,
125
+ "top_p": 1.0,
126
+ "torch_dtype": "bfloat16",
127
+ "torchscript": false,
128
+ "typical_p": 1.0,
129
+ "use_bfloat16": false,
130
+ "use_cache": true,
131
+ "use_sliding_window": false,
132
+ "video_token_id": null,
133
+ "vision_end_token_id": 151653,
134
+ "vision_start_token_id": 151652,
135
+ "vision_token_id": 151654,
136
+ "vocab_size": 151936
137
+ },
138
+ "torch_dtype": "bfloat16",
139
+ "use_cache": true,
140
+ "use_sliding_window": false,
141
+ "video_token_id": 151656,
142
+ "vision_config": {
143
+ "_name_or_path": "",
144
+ "add_cross_attention": false,
145
+ "architectures": null,
146
+ "bad_words_ids": null,
147
+ "begin_suppress_tokens": null,
148
+ "bos_token_id": null,
149
+ "chunk_size_feed_forward": 0,
150
+ "cross_attention_hidden_size": null,
151
+ "decoder_start_token_id": null,
152
+ "depth": 32,
153
+ "diversity_penalty": 0.0,
154
+ "do_sample": false,
155
+ "early_stopping": false,
156
+ "encoder_no_repeat_ngram_size": 0,
157
+ "eos_token_id": null,
158
+ "exponential_decay_length_penalty": null,
159
+ "finetuning_task": null,
160
+ "forced_bos_token_id": null,
161
+ "forced_eos_token_id": null,
162
+ "fullatt_block_indexes": [
163
+ 7,
164
+ 15,
165
+ 23,
166
+ 31
167
+ ],
168
+ "hidden_act": "silu",
169
+ "hidden_size": 1280,
170
+ "id2label": {
171
+ "0": "LABEL_0",
172
+ "1": "LABEL_1"
173
+ },
174
+ "in_channels": 3,
175
+ "in_chans": 3,
176
+ "initializer_range": 0.02,
177
+ "intermediate_size": 3420,
178
+ "is_decoder": false,
179
+ "is_encoder_decoder": false,
180
+ "label2id": {
181
+ "LABEL_0": 0,
182
+ "LABEL_1": 1
183
+ },
184
+ "length_penalty": 1.0,
185
+ "max_length": 20,
186
+ "min_length": 0,
187
+ "model_type": "qwen2_5_vl",
188
+ "no_repeat_ngram_size": 0,
189
+ "num_beam_groups": 1,
190
+ "num_beams": 1,
191
+ "num_heads": 16,
192
+ "num_return_sequences": 1,
193
+ "out_hidden_size": 2048,
194
+ "output_attentions": false,
195
+ "output_hidden_states": false,
196
+ "output_scores": false,
197
+ "pad_token_id": null,
198
+ "patch_size": 14,
199
+ "prefix": null,
200
+ "problem_type": null,
201
+ "pruned_heads": {},
202
+ "remove_invalid_values": false,
203
+ "repetition_penalty": 1.0,
204
+ "return_dict": true,
205
+ "return_dict_in_generate": false,
206
+ "sep_token_id": null,
207
+ "spatial_merge_size": 2,
208
+ "spatial_patch_size": 14,
209
+ "suppress_tokens": null,
210
+ "task_specific_params": null,
211
+ "temperature": 1.0,
212
+ "temporal_patch_size": 2,
213
+ "tf_legacy_loss": false,
214
+ "tie_encoder_decoder": false,
215
+ "tie_word_embeddings": true,
216
+ "tokenizer_class": null,
217
+ "tokens_per_second": 2,
218
+ "top_k": 50,
219
+ "top_p": 1.0,
220
+ "torch_dtype": "bfloat16",
221
+ "torchscript": false,
222
+ "typical_p": 1.0,
223
+ "use_bfloat16": false,
224
+ "window_size": 112
225
+ },
226
+ "vision_end_token_id": 151653,
227
+ "vision_start_token_id": 151652,
228
+ "vision_token_id": 151654,
229
+ "vocab_size": 151936
230
+ }
231
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": null,
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "pad_token_id": 151643,
10
+ "repetition_penalty": 1.05,
11
+ "temperature": 0.1,
12
+ "top_k": 1,
13
+ "top_p": 0.001,
14
+ "transformers_version": "4.51.3"
15
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12997a0e45f08c40b54bc57bc1e7cc046ffa921c514b5ba437c6f931b8b06e43
3
+ size 3073873661
model.safetensors.index.json ADDED
@@ -0,0 +1,833 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7509770496
4
+ },
5
+ "weight_map": {
6
+ "embedding_proj_layer.bias": "model-00002-of-00002.safetensors",
7
+ "embedding_proj_layer.weight": "model-00002-of-00002.safetensors",
8
+ "vlm.model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
9
+ "vlm.model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
10
+ "vlm.model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
+ "vlm.model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
12
+ "vlm.model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
13
+ "vlm.model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
14
+ "vlm.model.language_model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
15
+ "vlm.model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
16
+ "vlm.model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
17
+ "vlm.model.language_model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
18
+ "vlm.model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
19
+ "vlm.model.language_model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
20
+ "vlm.model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
21
+ "vlm.model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "vlm.model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
23
+ "vlm.model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
24
+ "vlm.model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
25
+ "vlm.model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
26
+ "vlm.model.language_model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
27
+ "vlm.model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
28
+ "vlm.model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
29
+ "vlm.model.language_model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
30
+ "vlm.model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
31
+ "vlm.model.language_model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
32
+ "vlm.model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
33
+ "vlm.model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "vlm.model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
35
+ "vlm.model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
36
+ "vlm.model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
37
+ "vlm.model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
38
+ "vlm.model.language_model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
39
+ "vlm.model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
+ "vlm.model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
+ "vlm.model.language_model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
42
+ "vlm.model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "vlm.model.language_model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
44
+ "vlm.model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
45
+ "vlm.model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "vlm.model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
47
+ "vlm.model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
48
+ "vlm.model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
49
+ "vlm.model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
50
+ "vlm.model.language_model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
51
+ "vlm.model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
52
+ "vlm.model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
53
+ "vlm.model.language_model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
54
+ "vlm.model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
55
+ "vlm.model.language_model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
56
+ "vlm.model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
57
+ "vlm.model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "vlm.model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
59
+ "vlm.model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
60
+ "vlm.model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
61
+ "vlm.model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
62
+ "vlm.model.language_model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
63
+ "vlm.model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
64
+ "vlm.model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
65
+ "vlm.model.language_model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
66
+ "vlm.model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
67
+ "vlm.model.language_model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
68
+ "vlm.model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
69
+ "vlm.model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "vlm.model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
71
+ "vlm.model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
72
+ "vlm.model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
73
+ "vlm.model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
74
+ "vlm.model.language_model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
75
+ "vlm.model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
+ "vlm.model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
+ "vlm.model.language_model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
78
+ "vlm.model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "vlm.model.language_model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
80
+ "vlm.model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
+ "vlm.model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "vlm.model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
83
+ "vlm.model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
84
+ "vlm.model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
85
+ "vlm.model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "vlm.model.language_model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
87
+ "vlm.model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
88
+ "vlm.model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
89
+ "vlm.model.language_model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
90
+ "vlm.model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
91
+ "vlm.model.language_model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
92
+ "vlm.model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
93
+ "vlm.model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "vlm.model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
95
+ "vlm.model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
96
+ "vlm.model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
97
+ "vlm.model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
98
+ "vlm.model.language_model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
99
+ "vlm.model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
100
+ "vlm.model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
101
+ "vlm.model.language_model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
102
+ "vlm.model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
103
+ "vlm.model.language_model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
104
+ "vlm.model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
105
+ "vlm.model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
106
+ "vlm.model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
107
+ "vlm.model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
108
+ "vlm.model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
109
+ "vlm.model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
110
+ "vlm.model.language_model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
111
+ "vlm.model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
+ "vlm.model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
+ "vlm.model.language_model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
114
+ "vlm.model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "vlm.model.language_model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
116
+ "vlm.model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
117
+ "vlm.model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "vlm.model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
119
+ "vlm.model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
120
+ "vlm.model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
121
+ "vlm.model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
122
+ "vlm.model.language_model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
123
+ "vlm.model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
124
+ "vlm.model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
125
+ "vlm.model.language_model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
126
+ "vlm.model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
127
+ "vlm.model.language_model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
128
+ "vlm.model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
129
+ "vlm.model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "vlm.model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
+ "vlm.model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
132
+ "vlm.model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
133
+ "vlm.model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "vlm.model.language_model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
135
+ "vlm.model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
136
+ "vlm.model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
137
+ "vlm.model.language_model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
138
+ "vlm.model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
139
+ "vlm.model.language_model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
140
+ "vlm.model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
141
+ "vlm.model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
142
+ "vlm.model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
143
+ "vlm.model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
144
+ "vlm.model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
145
+ "vlm.model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
146
+ "vlm.model.language_model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
147
+ "vlm.model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
148
+ "vlm.model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
149
+ "vlm.model.language_model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
150
+ "vlm.model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "vlm.model.language_model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
152
+ "vlm.model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
153
+ "vlm.model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "vlm.model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
155
+ "vlm.model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
156
+ "vlm.model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
157
+ "vlm.model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
158
+ "vlm.model.language_model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
159
+ "vlm.model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
160
+ "vlm.model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
161
+ "vlm.model.language_model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
162
+ "vlm.model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
163
+ "vlm.model.language_model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
164
+ "vlm.model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
165
+ "vlm.model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
166
+ "vlm.model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
167
+ "vlm.model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
168
+ "vlm.model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
169
+ "vlm.model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
170
+ "vlm.model.language_model.layers.20.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
171
+ "vlm.model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
172
+ "vlm.model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
173
+ "vlm.model.language_model.layers.20.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
174
+ "vlm.model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
175
+ "vlm.model.language_model.layers.20.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
176
+ "vlm.model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
177
+ "vlm.model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "vlm.model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
179
+ "vlm.model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
180
+ "vlm.model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
181
+ "vlm.model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
182
+ "vlm.model.language_model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
183
+ "vlm.model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
184
+ "vlm.model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
185
+ "vlm.model.language_model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
186
+ "vlm.model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
+ "vlm.model.language_model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
188
+ "vlm.model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
189
+ "vlm.model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
190
+ "vlm.model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
191
+ "vlm.model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
192
+ "vlm.model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
193
+ "vlm.model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
194
+ "vlm.model.language_model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
195
+ "vlm.model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
196
+ "vlm.model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
197
+ "vlm.model.language_model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
198
+ "vlm.model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
199
+ "vlm.model.language_model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
200
+ "vlm.model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
201
+ "vlm.model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
202
+ "vlm.model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
203
+ "vlm.model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
204
+ "vlm.model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
205
+ "vlm.model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
206
+ "vlm.model.language_model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
207
+ "vlm.model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
208
+ "vlm.model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
209
+ "vlm.model.language_model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
210
+ "vlm.model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
211
+ "vlm.model.language_model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
212
+ "vlm.model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
213
+ "vlm.model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
214
+ "vlm.model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
215
+ "vlm.model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
216
+ "vlm.model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
217
+ "vlm.model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
218
+ "vlm.model.language_model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
219
+ "vlm.model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
220
+ "vlm.model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
221
+ "vlm.model.language_model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
222
+ "vlm.model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
223
+ "vlm.model.language_model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
224
+ "vlm.model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
225
+ "vlm.model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
226
+ "vlm.model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
227
+ "vlm.model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
228
+ "vlm.model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
229
+ "vlm.model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
230
+ "vlm.model.language_model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
231
+ "vlm.model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
232
+ "vlm.model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
233
+ "vlm.model.language_model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
234
+ "vlm.model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
235
+ "vlm.model.language_model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
236
+ "vlm.model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
237
+ "vlm.model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
238
+ "vlm.model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
239
+ "vlm.model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
240
+ "vlm.model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
241
+ "vlm.model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
242
+ "vlm.model.language_model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
243
+ "vlm.model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
244
+ "vlm.model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
245
+ "vlm.model.language_model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
246
+ "vlm.model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
247
+ "vlm.model.language_model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
248
+ "vlm.model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
249
+ "vlm.model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
250
+ "vlm.model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
251
+ "vlm.model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
252
+ "vlm.model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
253
+ "vlm.model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
254
+ "vlm.model.language_model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
255
+ "vlm.model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
256
+ "vlm.model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
257
+ "vlm.model.language_model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
258
+ "vlm.model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
259
+ "vlm.model.language_model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
260
+ "vlm.model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
261
+ "vlm.model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
262
+ "vlm.model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
263
+ "vlm.model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
264
+ "vlm.model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
265
+ "vlm.model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
266
+ "vlm.model.language_model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
267
+ "vlm.model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
268
+ "vlm.model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
269
+ "vlm.model.language_model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
270
+ "vlm.model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
271
+ "vlm.model.language_model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
272
+ "vlm.model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
273
+ "vlm.model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
274
+ "vlm.model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
275
+ "vlm.model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
276
+ "vlm.model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
277
+ "vlm.model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
278
+ "vlm.model.language_model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
279
+ "vlm.model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
280
+ "vlm.model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
281
+ "vlm.model.language_model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
282
+ "vlm.model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
283
+ "vlm.model.language_model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
284
+ "vlm.model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
285
+ "vlm.model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
286
+ "vlm.model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
287
+ "vlm.model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
288
+ "vlm.model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
289
+ "vlm.model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
290
+ "vlm.model.language_model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
291
+ "vlm.model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
292
+ "vlm.model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
293
+ "vlm.model.language_model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
294
+ "vlm.model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
+ "vlm.model.language_model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
296
+ "vlm.model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
297
+ "vlm.model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
298
+ "vlm.model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
299
+ "vlm.model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
300
+ "vlm.model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
301
+ "vlm.model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
302
+ "vlm.model.language_model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
303
+ "vlm.model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
304
+ "vlm.model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
305
+ "vlm.model.language_model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
306
+ "vlm.model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
307
+ "vlm.model.language_model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
308
+ "vlm.model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
309
+ "vlm.model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
310
+ "vlm.model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
311
+ "vlm.model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
312
+ "vlm.model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
313
+ "vlm.model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
314
+ "vlm.model.language_model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
315
+ "vlm.model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
316
+ "vlm.model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
317
+ "vlm.model.language_model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
318
+ "vlm.model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
319
+ "vlm.model.language_model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
320
+ "vlm.model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
321
+ "vlm.model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
322
+ "vlm.model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
323
+ "vlm.model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
324
+ "vlm.model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
325
+ "vlm.model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
326
+ "vlm.model.language_model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
327
+ "vlm.model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
328
+ "vlm.model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
329
+ "vlm.model.language_model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
330
+ "vlm.model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
331
+ "vlm.model.language_model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
332
+ "vlm.model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
333
+ "vlm.model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
334
+ "vlm.model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
335
+ "vlm.model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
336
+ "vlm.model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
337
+ "vlm.model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
338
+ "vlm.model.language_model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
339
+ "vlm.model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
340
+ "vlm.model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
341
+ "vlm.model.language_model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
342
+ "vlm.model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
343
+ "vlm.model.language_model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
344
+ "vlm.model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
345
+ "vlm.model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
346
+ "vlm.model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
347
+ "vlm.model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
348
+ "vlm.model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
349
+ "vlm.model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
350
+ "vlm.model.language_model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
351
+ "vlm.model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
352
+ "vlm.model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
353
+ "vlm.model.language_model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
354
+ "vlm.model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
355
+ "vlm.model.language_model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
356
+ "vlm.model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
357
+ "vlm.model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
358
+ "vlm.model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
359
+ "vlm.model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
360
+ "vlm.model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
361
+ "vlm.model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
362
+ "vlm.model.language_model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
363
+ "vlm.model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
364
+ "vlm.model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
365
+ "vlm.model.language_model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
366
+ "vlm.model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
367
+ "vlm.model.language_model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
368
+ "vlm.model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
369
+ "vlm.model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
370
+ "vlm.model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
371
+ "vlm.model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
372
+ "vlm.model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
373
+ "vlm.model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
374
+ "vlm.model.language_model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
375
+ "vlm.model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
376
+ "vlm.model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
377
+ "vlm.model.language_model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
378
+ "vlm.model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
379
+ "vlm.model.language_model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
380
+ "vlm.model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
381
+ "vlm.model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
382
+ "vlm.model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
383
+ "vlm.model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
384
+ "vlm.model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
385
+ "vlm.model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
386
+ "vlm.model.language_model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
387
+ "vlm.model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
388
+ "vlm.model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
389
+ "vlm.model.language_model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
390
+ "vlm.model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
391
+ "vlm.model.language_model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
392
+ "vlm.model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
393
+ "vlm.model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
394
+ "vlm.model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
395
+ "vlm.model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
396
+ "vlm.model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
397
+ "vlm.model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "vlm.model.language_model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
399
+ "vlm.model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
+ "vlm.model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
401
+ "vlm.model.language_model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
402
+ "vlm.model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
403
+ "vlm.model.language_model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
404
+ "vlm.model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
405
+ "vlm.model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
406
+ "vlm.model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
407
+ "vlm.model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
408
+ "vlm.model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
409
+ "vlm.model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
410
+ "vlm.model.language_model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
411
+ "vlm.model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
412
+ "vlm.model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
413
+ "vlm.model.language_model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
414
+ "vlm.model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
415
+ "vlm.model.language_model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
416
+ "vlm.model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
417
+ "vlm.model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
418
+ "vlm.model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
419
+ "vlm.model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
420
+ "vlm.model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
421
+ "vlm.model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
422
+ "vlm.model.language_model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
423
+ "vlm.model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
424
+ "vlm.model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
425
+ "vlm.model.language_model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
426
+ "vlm.model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
427
+ "vlm.model.language_model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
428
+ "vlm.model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
429
+ "vlm.model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
430
+ "vlm.model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
431
+ "vlm.model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
432
+ "vlm.model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
433
+ "vlm.model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
434
+ "vlm.model.language_model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
435
+ "vlm.model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
436
+ "vlm.model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
437
+ "vlm.model.language_model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
438
+ "vlm.model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
439
+ "vlm.model.language_model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
440
+ "vlm.model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
441
+ "vlm.model.language_model.norm.weight": "model-00002-of-00002.safetensors",
442
+ "vlm.model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
443
+ "vlm.model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
444
+ "vlm.model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
445
+ "vlm.model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
446
+ "vlm.model.visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
447
+ "vlm.model.visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
448
+ "vlm.model.visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
449
+ "vlm.model.visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
450
+ "vlm.model.visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
451
+ "vlm.model.visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
452
+ "vlm.model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
453
+ "vlm.model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
454
+ "vlm.model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
455
+ "vlm.model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
456
+ "vlm.model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
457
+ "vlm.model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
458
+ "vlm.model.visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
459
+ "vlm.model.visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
460
+ "vlm.model.visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
461
+ "vlm.model.visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
462
+ "vlm.model.visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
463
+ "vlm.model.visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
464
+ "vlm.model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
465
+ "vlm.model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
466
+ "vlm.model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
467
+ "vlm.model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
468
+ "vlm.model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
469
+ "vlm.model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
470
+ "vlm.model.visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
471
+ "vlm.model.visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
472
+ "vlm.model.visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
473
+ "vlm.model.visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
474
+ "vlm.model.visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
475
+ "vlm.model.visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
476
+ "vlm.model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
477
+ "vlm.model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
478
+ "vlm.model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
479
+ "vlm.model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
480
+ "vlm.model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
481
+ "vlm.model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
482
+ "vlm.model.visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
483
+ "vlm.model.visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
484
+ "vlm.model.visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
485
+ "vlm.model.visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
486
+ "vlm.model.visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
487
+ "vlm.model.visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
488
+ "vlm.model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
489
+ "vlm.model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
490
+ "vlm.model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
491
+ "vlm.model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
492
+ "vlm.model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
493
+ "vlm.model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
494
+ "vlm.model.visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
495
+ "vlm.model.visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
496
+ "vlm.model.visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
497
+ "vlm.model.visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
498
+ "vlm.model.visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
499
+ "vlm.model.visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
500
+ "vlm.model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
501
+ "vlm.model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
502
+ "vlm.model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
503
+ "vlm.model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
504
+ "vlm.model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
505
+ "vlm.model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
506
+ "vlm.model.visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
507
+ "vlm.model.visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
508
+ "vlm.model.visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
509
+ "vlm.model.visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
510
+ "vlm.model.visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
511
+ "vlm.model.visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
512
+ "vlm.model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
513
+ "vlm.model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
514
+ "vlm.model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
515
+ "vlm.model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
516
+ "vlm.model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
517
+ "vlm.model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
518
+ "vlm.model.visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
519
+ "vlm.model.visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
520
+ "vlm.model.visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
521
+ "vlm.model.visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
522
+ "vlm.model.visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
523
+ "vlm.model.visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
524
+ "vlm.model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
525
+ "vlm.model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
526
+ "vlm.model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
527
+ "vlm.model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
528
+ "vlm.model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
529
+ "vlm.model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
530
+ "vlm.model.visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
531
+ "vlm.model.visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
532
+ "vlm.model.visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
533
+ "vlm.model.visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
534
+ "vlm.model.visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
535
+ "vlm.model.visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
536
+ "vlm.model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
537
+ "vlm.model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
538
+ "vlm.model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
539
+ "vlm.model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
540
+ "vlm.model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
541
+ "vlm.model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
542
+ "vlm.model.visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
543
+ "vlm.model.visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
544
+ "vlm.model.visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
545
+ "vlm.model.visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
546
+ "vlm.model.visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
547
+ "vlm.model.visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
548
+ "vlm.model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
549
+ "vlm.model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
550
+ "vlm.model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
551
+ "vlm.model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
552
+ "vlm.model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
553
+ "vlm.model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
554
+ "vlm.model.visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
555
+ "vlm.model.visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
556
+ "vlm.model.visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
557
+ "vlm.model.visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
558
+ "vlm.model.visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
559
+ "vlm.model.visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
560
+ "vlm.model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
561
+ "vlm.model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
562
+ "vlm.model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
563
+ "vlm.model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
564
+ "vlm.model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
565
+ "vlm.model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
566
+ "vlm.model.visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
567
+ "vlm.model.visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
568
+ "vlm.model.visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
569
+ "vlm.model.visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
570
+ "vlm.model.visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
571
+ "vlm.model.visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
572
+ "vlm.model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
573
+ "vlm.model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
574
+ "vlm.model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
575
+ "vlm.model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
576
+ "vlm.model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
577
+ "vlm.model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
578
+ "vlm.model.visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
579
+ "vlm.model.visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
580
+ "vlm.model.visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
581
+ "vlm.model.visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
582
+ "vlm.model.visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
583
+ "vlm.model.visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
584
+ "vlm.model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
585
+ "vlm.model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
586
+ "vlm.model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
587
+ "vlm.model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
588
+ "vlm.model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
589
+ "vlm.model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
590
+ "vlm.model.visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
591
+ "vlm.model.visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
592
+ "vlm.model.visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
593
+ "vlm.model.visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
594
+ "vlm.model.visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
595
+ "vlm.model.visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
596
+ "vlm.model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
597
+ "vlm.model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
598
+ "vlm.model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
599
+ "vlm.model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
600
+ "vlm.model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
601
+ "vlm.model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
602
+ "vlm.model.visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
603
+ "vlm.model.visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
604
+ "vlm.model.visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
605
+ "vlm.model.visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
606
+ "vlm.model.visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
607
+ "vlm.model.visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
608
+ "vlm.model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
609
+ "vlm.model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
610
+ "vlm.model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
611
+ "vlm.model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
612
+ "vlm.model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
613
+ "vlm.model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
614
+ "vlm.model.visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
615
+ "vlm.model.visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
616
+ "vlm.model.visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
617
+ "vlm.model.visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
618
+ "vlm.model.visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
619
+ "vlm.model.visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
620
+ "vlm.model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
621
+ "vlm.model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
622
+ "vlm.model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
623
+ "vlm.model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
624
+ "vlm.model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
625
+ "vlm.model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
626
+ "vlm.model.visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
627
+ "vlm.model.visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
628
+ "vlm.model.visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
629
+ "vlm.model.visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
630
+ "vlm.model.visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
631
+ "vlm.model.visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
632
+ "vlm.model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
633
+ "vlm.model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
634
+ "vlm.model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
635
+ "vlm.model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
636
+ "vlm.model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
637
+ "vlm.model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
638
+ "vlm.model.visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
639
+ "vlm.model.visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
640
+ "vlm.model.visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
641
+ "vlm.model.visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
642
+ "vlm.model.visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
643
+ "vlm.model.visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
644
+ "vlm.model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
645
+ "vlm.model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
646
+ "vlm.model.visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
647
+ "vlm.model.visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
648
+ "vlm.model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
649
+ "vlm.model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
650
+ "vlm.model.visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
651
+ "vlm.model.visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
652
+ "vlm.model.visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
653
+ "vlm.model.visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
654
+ "vlm.model.visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
655
+ "vlm.model.visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
656
+ "vlm.model.visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
657
+ "vlm.model.visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
658
+ "vlm.model.visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
659
+ "vlm.model.visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
660
+ "vlm.model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
661
+ "vlm.model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
662
+ "vlm.model.visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
663
+ "vlm.model.visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
664
+ "vlm.model.visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
665
+ "vlm.model.visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
666
+ "vlm.model.visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
667
+ "vlm.model.visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
668
+ "vlm.model.visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
669
+ "vlm.model.visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
670
+ "vlm.model.visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
671
+ "vlm.model.visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
672
+ "vlm.model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
673
+ "vlm.model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
674
+ "vlm.model.visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
675
+ "vlm.model.visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
676
+ "vlm.model.visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
677
+ "vlm.model.visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
678
+ "vlm.model.visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
679
+ "vlm.model.visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
680
+ "vlm.model.visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
681
+ "vlm.model.visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
682
+ "vlm.model.visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
683
+ "vlm.model.visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
684
+ "vlm.model.visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
685
+ "vlm.model.visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
686
+ "vlm.model.visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
687
+ "vlm.model.visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
688
+ "vlm.model.visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
689
+ "vlm.model.visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
690
+ "vlm.model.visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
691
+ "vlm.model.visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
692
+ "vlm.model.visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
693
+ "vlm.model.visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
694
+ "vlm.model.visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
695
+ "vlm.model.visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
696
+ "vlm.model.visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
697
+ "vlm.model.visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
698
+ "vlm.model.visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
699
+ "vlm.model.visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
700
+ "vlm.model.visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
701
+ "vlm.model.visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
702
+ "vlm.model.visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
703
+ "vlm.model.visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
704
+ "vlm.model.visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
705
+ "vlm.model.visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
706
+ "vlm.model.visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
707
+ "vlm.model.visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
708
+ "vlm.model.visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
709
+ "vlm.model.visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
710
+ "vlm.model.visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
711
+ "vlm.model.visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
712
+ "vlm.model.visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
713
+ "vlm.model.visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
714
+ "vlm.model.visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
715
+ "vlm.model.visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
716
+ "vlm.model.visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
717
+ "vlm.model.visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
718
+ "vlm.model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
719
+ "vlm.model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
720
+ "vlm.model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
721
+ "vlm.model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
722
+ "vlm.model.visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
723
+ "vlm.model.visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
724
+ "vlm.model.visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
725
+ "vlm.model.visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
726
+ "vlm.model.visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
727
+ "vlm.model.visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
728
+ "vlm.model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
729
+ "vlm.model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
730
+ "vlm.model.visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
731
+ "vlm.model.visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
732
+ "vlm.model.visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
733
+ "vlm.model.visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
734
+ "vlm.model.visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
735
+ "vlm.model.visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
736
+ "vlm.model.visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
737
+ "vlm.model.visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
738
+ "vlm.model.visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
739
+ "vlm.model.visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
740
+ "vlm.model.visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
741
+ "vlm.model.visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
742
+ "vlm.model.visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
743
+ "vlm.model.visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
744
+ "vlm.model.visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
745
+ "vlm.model.visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
746
+ "vlm.model.visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
747
+ "vlm.model.visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
748
+ "vlm.model.visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
749
+ "vlm.model.visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
750
+ "vlm.model.visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
751
+ "vlm.model.visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
752
+ "vlm.model.visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
753
+ "vlm.model.visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
754
+ "vlm.model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
755
+ "vlm.model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
756
+ "vlm.model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
757
+ "vlm.model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
758
+ "vlm.model.visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
759
+ "vlm.model.visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
760
+ "vlm.model.visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
761
+ "vlm.model.visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
762
+ "vlm.model.visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
763
+ "vlm.model.visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
764
+ "vlm.model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
765
+ "vlm.model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
766
+ "vlm.model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
767
+ "vlm.model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
768
+ "vlm.model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
769
+ "vlm.model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
770
+ "vlm.model.visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
771
+ "vlm.model.visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
772
+ "vlm.model.visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
773
+ "vlm.model.visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
774
+ "vlm.model.visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
775
+ "vlm.model.visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
776
+ "vlm.model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
777
+ "vlm.model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
778
+ "vlm.model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
779
+ "vlm.model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
780
+ "vlm.model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
781
+ "vlm.model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
782
+ "vlm.model.visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
783
+ "vlm.model.visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
784
+ "vlm.model.visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
785
+ "vlm.model.visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
786
+ "vlm.model.visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
787
+ "vlm.model.visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
788
+ "vlm.model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
789
+ "vlm.model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
790
+ "vlm.model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
791
+ "vlm.model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
792
+ "vlm.model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
793
+ "vlm.model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
794
+ "vlm.model.visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
795
+ "vlm.model.visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
796
+ "vlm.model.visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
797
+ "vlm.model.visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
798
+ "vlm.model.visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
799
+ "vlm.model.visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
800
+ "vlm.model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
801
+ "vlm.model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
802
+ "vlm.model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
803
+ "vlm.model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
804
+ "vlm.model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
805
+ "vlm.model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
806
+ "vlm.model.visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
807
+ "vlm.model.visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
808
+ "vlm.model.visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
809
+ "vlm.model.visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
810
+ "vlm.model.visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
811
+ "vlm.model.visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
812
+ "vlm.model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
813
+ "vlm.model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
814
+ "vlm.model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
815
+ "vlm.model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
816
+ "vlm.model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
817
+ "vlm.model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
818
+ "vlm.model.visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
819
+ "vlm.model.visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
820
+ "vlm.model.visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
821
+ "vlm.model.visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
822
+ "vlm.model.visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
823
+ "vlm.model.visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
824
+ "vlm.model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
825
+ "vlm.model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
826
+ "vlm.model.visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
827
+ "vlm.model.visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
828
+ "vlm.model.visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
829
+ "vlm.model.visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
830
+ "vlm.model.visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
831
+ "vlm.model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors"
832
+ }
833
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 602112,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "ColQwen2_5Processor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "max_pixels": 602112,
26
+ "min_pixels": 3136,
27
+ "longest_edge": 602112,
28
+ "shortest_edge": 3136
29
+ },
30
+ "temporal_patch_size": 2
31
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
tokenizer_config.json ADDED
@@ -0,0 +1,208 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "clean_up_tokenization_spaces": false,
199
+ "eos_token": "<|im_end|>",
200
+ "errors": "replace",
201
+ "extra_special_tokens": {},
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "processor_class": "ColQwen2_5_Processor",
205
+ "split_special_tokens": false,
206
+ "tokenizer_class": "Qwen2Tokenizer",
207
+ "unk_token": null
208
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff