Hugging Face's logo

xiaomi-research
/
SpatioLM-Understanding-InternVL3.5

Image-Text-to-Text
Transformers
Safetensors
internvl_chat
multimodal
vision-language
spatial-reasoning
spatiolm
conversational
Model card Files
xet
 Community
edatai commited on
Commit
fcfd7d4
·
verified ·
1 Parent(s): bf22522

Upload model checkpoint

Browse files
Files changed (16) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +37 -0
  3. chat_template.jinja +6 -0
  4. config.json +299 -0
  5. generation_config.json +5 -0
  6. merges.txt +0 -0
  7. model-00001-of-00004.safetensors +3 -0
  8. model-00002-of-00004.safetensors +3 -0
  9. model-00003-of-00004.safetensors +3 -0
  10. model-00004-of-00004.safetensors +3 -0
  11. model.safetensors.index.json +0 -0
  12. preprocessor_config.json +34 -0
  13. special_tokens_map.json +40 -0
  14. tokenizer.json +3 -0
  15. tokenizer_config.json +322 -0
  16. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 151677,
3
+ "</img>": 151670,
4
+ "</quad>": 151673,
5
+ "</ref>": 151675,
6
+ "</think>": 151668,
7
+ "</tool_call>": 151658,
8
+ "</tool_response>": 151666,
9
+ "<IMG_CONTEXT>": 151671,
10
+ "<box>": 151676,
11
+ "<img>": 151669,
12
+ "<quad>": 151672,
13
+ "<ref>": 151674,
14
+ "<think>": 151667,
15
+ "<tool_call>": 151657,
16
+ "<tool_response>": 151665,
17
+ "<|box_end|>": 151649,
18
+ "<|box_start|>": 151648,
19
+ "<|endoftext|>": 151643,
20
+ "<|file_sep|>": 151664,
21
+ "<|fim_middle|>": 151660,
22
+ "<|fim_pad|>": 151662,
23
+ "<|fim_prefix|>": 151659,
24
+ "<|fim_suffix|>": 151661,
25
+ "<|im_end|>": 151645,
26
+ "<|im_start|>": 151644,
27
+ "<|image_pad|>": 151655,
28
+ "<|object_ref_end|>": 151647,
29
+ "<|object_ref_start|>": 151646,
30
+ "<|quad_end|>": 151651,
31
+ "<|quad_start|>": 151650,
32
+ "<|repo_name|>": 151663,
33
+ "<|video_pad|>": 151656,
34
+ "<|vision_end|>": 151653,
35
+ "<|vision_pad|>": 151654,
36
+ "<|vision_start|>": 151652
37
+ }
chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ '}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<image>
3
+ ' }}{% elif content['type'] == 'video' %}{{ '<video>
4
+ ' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
6
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,299 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "InternVL3RChatModel"
4
+ ],
5
+ "downsample_ratio": 0.5,
6
+ "dtype": "bfloat16",
7
+ "dynamic_image_size": true,
8
+ "eos_token_id": 151645,
9
+ "force_image_size": 448,
10
+ "hidden_size": 4096,
11
+ "keys_to_ignore_at_inference": [
12
+ "past_key_values"
13
+ ],
14
+ "llm_config": {
15
+ "architectures": [
16
+ "Qwen3ForV3RCausalLM"
17
+ ],
18
+ "attention_bias": false,
19
+ "attention_dropout": 0.0,
20
+ "bos_token_id": 151643,
21
+ "debug": false,
22
+ "dtype": "bfloat16",
23
+ "eos_token_id": 151645,
24
+ "ep_size": 1,
25
+ "head_dim": 128,
26
+ "hidden_act": "silu",
27
+ "hidden_size": 4096,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 12288,
30
+ "layer_types": [
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention"
67
+ ],
68
+ "max_position_embeddings": 40960,
69
+ "max_window_layers": 36,
70
+ "micro_forward": false,
71
+ "model_type": "qwen3_v3r",
72
+ "num_attention_heads": 32,
73
+ "num_hidden_layers": 36,
74
+ "num_key_value_heads": 8,
75
+ "pad_token_id": 151643,
76
+ "rms_norm_eps": 1e-06,
77
+ "rope_scaling": null,
78
+ "rope_theta": 1000000,
79
+ "skip_checkpoint": false,
80
+ "sliding_window": null,
81
+ "use_cache": false,
82
+ "use_deepep": false,
83
+ "use_sliding_window": false,
84
+ "vision3r_head_dim": 32,
85
+ "vision3r_intermediate_size": 1024,
86
+ "vision3r_layer_ids": [
87
+ 4,
88
+ 8,
89
+ 12,
90
+ 16,
91
+ 20,
92
+ 24
93
+ ],
94
+ "vision3r_num_attention_heads": 16,
95
+ "vocab_size": 151936
96
+ },
97
+ "max_dynamic_patch": 12,
98
+ "min_dynamic_patch": 1,
99
+ "model_type": "internvl_chat",
100
+ "output_attentions": false,
101
+ "pad2square": false,
102
+ "pad_token_id": 151643,
103
+ "ps_version": "v2",
104
+ "select_layer": 18,
105
+ "template": "internvl2_5",
106
+ "tie_word_embeddings": false,
107
+ "transformers_version": null,
108
+ "use_backbone_lora": 0,
109
+ "use_llm_lora": 0,
110
+ "use_thumbnail": true,
111
+ "vision_condition_config": null,
112
+ "vision_config": {
113
+ "architectures": [
114
+ "InternVisionModel"
115
+ ],
116
+ "attention_dropout": 0.0,
117
+ "drop_path_rate": 0.1,
118
+ "dropout": 0.0,
119
+ "dtype": "bfloat16",
120
+ "hidden_act": "gelu",
121
+ "hidden_size": 1024,
122
+ "image_size": 448,
123
+ "initializer_factor": 1.0,
124
+ "initializer_range": 0.02,
125
+ "intermediate_size": 4096,
126
+ "layer_norm_eps": 1e-06,
127
+ "model_type": "intern_vit_6b",
128
+ "norm_type": "layer_norm",
129
+ "num_attention_heads": 16,
130
+ "num_channels": 3,
131
+ "num_hidden_layers": 24,
132
+ "pad_token_id": 151643,
133
+ "patch_size": 14,
134
+ "qk_normalization": false,
135
+ "qkv_bias": true,
136
+ "use_fa3": false,
137
+ "use_flash_attn": true
138
+ },
139
+ "vision_dpt_config": {
140
+ "_name_or_path": "",
141
+ "add_cross_attention": false,
142
+ "architectures": null,
143
+ "bad_words_ids": null,
144
+ "begin_suppress_tokens": null,
145
+ "bos_token_id": null,
146
+ "chunk_size_feed_forward": 0,
147
+ "cross_attention_hidden_size": null,
148
+ "decoder_start_token_id": null,
149
+ "diversity_penalty": 0.0,
150
+ "do_sample": false,
151
+ "dpt_config": {
152
+ "_name_or_path": "",
153
+ "add_cross_attention": false,
154
+ "alt_start": 8,
155
+ "architectures": [
156
+ "DA3Model"
157
+ ],
158
+ "backbone_name": "vitl",
159
+ "bad_words_ids": null,
160
+ "begin_suppress_tokens": null,
161
+ "bos_token_id": null,
162
+ "camera_dec_dim_in": 2048,
163
+ "camera_enc_dim_out": 1024,
164
+ "cat_token": true,
165
+ "chunk_size_feed_forward": 0,
166
+ "cross_attention_hidden_size": null,
167
+ "decoder_start_token_id": null,
168
+ "depth_dim_in": 4096,
169
+ "depth_dim_out": 2,
170
+ "depth_features": 256,
171
+ "depth_out_channels": [
172
+ 256,
173
+ 512,
174
+ 1024,
175
+ 1024
176
+ ],
177
+ "diversity_penalty": 0.0,
178
+ "do_sample": false,
179
+ "dtype": null,
180
+ "early_stopping": false,
181
+ "encoder_no_repeat_ngram_size": 0,
182
+ "eos_token_id": null,
183
+ "exponential_decay_length_penalty": null,
184
+ "finetuning_task": null,
185
+ "forced_bos_token_id": null,
186
+ "forced_eos_token_id": null,
187
+ "hidden_size": 4096,
188
+ "id2label": {
189
+ "0": "LABEL_0",
190
+ "1": "LABEL_1"
191
+ },
192
+ "image_size": 518,
193
+ "is_decoder": false,
194
+ "is_encoder_decoder": false,
195
+ "label2id": {
196
+ "LABEL_0": 0,
197
+ "LABEL_1": 1
198
+ },
199
+ "length_penalty": 1.0,
200
+ "max_length": 20,
201
+ "min_length": 0,
202
+ "model_type": "depth_anything_3",
203
+ "no_repeat_ngram_size": 0,
204
+ "num_beam_groups": 1,
205
+ "num_beams": 1,
206
+ "num_return_sequences": 1,
207
+ "out_layers": [
208
+ 11,
209
+ 15,
210
+ 19,
211
+ 23
212
+ ],
213
+ "output_attentions": false,
214
+ "output_hidden_states": false,
215
+ "output_scores": false,
216
+ "pad_token_id": 151643,
217
+ "patch_size": 14,
218
+ "prefix": null,
219
+ "problem_type": null,
220
+ "pruned_heads": {},
221
+ "qknorm_start": 8,
222
+ "remove_invalid_values": false,
223
+ "repetition_penalty": 1.0,
224
+ "return_dict": true,
225
+ "return_dict_in_generate": false,
226
+ "rope_start": 8,
227
+ "sep_token_id": null,
228
+ "suppress_tokens": null,
229
+ "task_specific_params": null,
230
+ "temperature": 1.0,
231
+ "tf_legacy_loss": false,
232
+ "tie_encoder_decoder": false,
233
+ "tie_word_embeddings": true,
234
+ "tokenizer_class": null,
235
+ "top_k": 50,
236
+ "top_p": 1.0,
237
+ "torchscript": false,
238
+ "transformers_version": "4.57.1",
239
+ "typical_p": 1.0,
240
+ "use_bfloat16": false
241
+ },
242
+ "dtype": "float32",
243
+ "early_stopping": false,
244
+ "encoder_no_repeat_ngram_size": 0,
245
+ "eos_token_id": null,
246
+ "exponential_decay_length_penalty": null,
247
+ "finetuning_task": null,
248
+ "forced_bos_token_id": null,
249
+ "forced_eos_token_id": null,
250
+ "id2label": {
251
+ "0": "LABEL_0",
252
+ "1": "LABEL_1"
253
+ },
254
+ "is_decoder": false,
255
+ "is_encoder_decoder": false,
256
+ "label2id": {
257
+ "LABEL_0": 0,
258
+ "LABEL_1": 1
259
+ },
260
+ "layer_ids": [
261
+ 0,
262
+ 2,
263
+ 4,
264
+ 6
265
+ ],
266
+ "length_penalty": 1.0,
267
+ "max_length": 20,
268
+ "min_length": 0,
269
+ "no_repeat_ngram_size": 0,
270
+ "num_beam_groups": 1,
271
+ "num_beams": 1,
272
+ "num_return_sequences": 1,
273
+ "output_attentions": false,
274
+ "output_hidden_states": false,
275
+ "output_scores": false,
276
+ "pad_token_id": null,
277
+ "prefix": null,
278
+ "problem_type": null,
279
+ "pruned_heads": {},
280
+ "remove_invalid_values": false,
281
+ "repetition_penalty": 1.0,
282
+ "return_dict": true,
283
+ "return_dict_in_generate": false,
284
+ "sep_token_id": null,
285
+ "suppress_tokens": null,
286
+ "task_specific_params": null,
287
+ "temperature": 1.0,
288
+ "tf_legacy_loss": false,
289
+ "tie_encoder_decoder": false,
290
+ "tie_word_embeddings": true,
291
+ "tokenizer_class": null,
292
+ "top_k": 50,
293
+ "top_p": 1.0,
294
+ "torchscript": false,
295
+ "transformers_version": null,
296
+ "typical_p": 1.0,
297
+ "use_bfloat16": false
298
+ }
299
+ }
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 151645,
4
+ "transformers_version": "4.57.1"
5
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d248cd50b11f03456eeb02431e28863f353e2dee4ec29abd470b65daad93e2dd
3
+ size 4990210776
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17791c90a9553b5f01cd8f77676ac4b49ba6c3e73e846321372e18cfc2624cca
3
+ size 4999848424
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4d82a8ecad18a696c54fad426d0da04b97b411b55bac209b3d4f7d83698a73e
3
+ size 4983071360
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb567794a9d47ad48e38a73aad4fd954adf19bc499c48f87c058c0d0de168da2
3
+ size 3079044660
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "crop_to_patches": false,
4
+ "data_format": "channels_first",
5
+ "default_to_square": true,
6
+ "device": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_rescale": true,
11
+ "do_resize": true,
12
+ "image_mean": [
13
+ 0.485,
14
+ 0.456,
15
+ 0.406
16
+ ],
17
+ "image_processor_type": "GotOcr2ImageProcessorFast",
18
+ "image_std": [
19
+ 0.229,
20
+ 0.224,
21
+ 0.225
22
+ ],
23
+ "input_data_format": null,
24
+ "max_patches": 12,
25
+ "min_patches": 1,
26
+ "processor_class": "InternVLProcessor",
27
+ "resample": 3,
28
+ "rescale_factor": 0.00392156862745098,
29
+ "return_tensors": null,
30
+ "size": {
31
+ "height": 448,
32
+ "width": 448
33
+ }
34
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<img>",
17
+ "</img>",
18
+ "<IMG_CONTEXT>",
19
+ "<quad>",
20
+ "</quad>",
21
+ "<ref>",
22
+ "</ref>",
23
+ "<box>",
24
+ "</box>"
25
+ ],
26
+ "eos_token": {
27
+ "content": "<|im_end|>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "<|endoftext|>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6581c44164d273d4222df982905a7e0450dcf3a4a7ebe98f9ec53e4de05beffe
3
+ size 11424300
tokenizer_config.json ADDED
@@ -0,0 +1,322 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "151645": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "151646": {
31
+ "content": "<|object_ref_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|object_ref_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "151648": {
47
+ "content": "<|box_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "151649": {
55
+ "content": "<|box_end|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "151665": {
183
+ "content": "<tool_response>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "151666": {
191
+ "content": "</tool_response>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "151667": {
199
+ "content": "<think>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
+ },
206
+ "151668": {
207
+ "content": "</think>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": false
213
+ },
214
+ "151669": {
215
+ "content": "<img>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "151670": {
223
+ "content": "</img>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "151671": {
231
+ "content": "<IMG_CONTEXT>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "151672": {
239
+ "content": "<quad>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "151673": {
247
+ "content": "</quad>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "151674": {
255
+ "content": "<ref>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "151675": {
263
+ "content": "</ref>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "151676": {
271
+ "content": "<box>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "151677": {
279
+ "content": "</box>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ }
286
+ },
287
+ "additional_special_tokens": [
288
+ "<|im_start|>",
289
+ "<|im_end|>",
290
+ "<|object_ref_start|>",
291
+ "<|object_ref_end|>",
292
+ "<|box_start|>",
293
+ "<|box_end|>",
294
+ "<|quad_start|>",
295
+ "<|quad_end|>",
296
+ "<|vision_start|>",
297
+ "<|vision_end|>",
298
+ "<|vision_pad|>",
299
+ "<|image_pad|>",
300
+ "<|video_pad|>",
301
+ "<img>",
302
+ "</img>",
303
+ "<IMG_CONTEXT>",
304
+ "<quad>",
305
+ "</quad>",
306
+ "<ref>",
307
+ "</ref>",
308
+ "<box>",
309
+ "</box>"
310
+ ],
311
+ "bos_token": null,
312
+ "clean_up_tokenization_spaces": false,
313
+ "eos_token": "<|im_end|>",
314
+ "errors": "replace",
315
+ "extra_special_tokens": {},
316
+ "model_max_length": 14588,
317
+ "pad_token": "<|endoftext|>",
318
+ "processor_class": "InternVLProcessor",
319
+ "split_special_tokens": false,
320
+ "tokenizer_class": "Qwen2Tokenizer",
321
+ "unk_token": null
322
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff