prince-canuma commited on
Commit
e0befd0
·
verified ·
1 Parent(s): 2f7b79d

Upload folder using huggingface_hub

Browse files
.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
README.md ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ pipeline_tag: image-text-to-text
6
+ tags:
7
+ - multimodal
8
+ - gui
9
+ - mlx
10
+ library_name: transformers
11
+ ---
12
+
13
+ # mlx-community/UI-TARS-72B-DPO-bf16
14
+ This model was converted to MLX format from [`bytedance-research/UI-TARS-72B-DPO`]() using mlx-vlm version **0.1.15**.
15
+ Refer to the [original model card](https://huggingface.co/bytedance-research/UI-TARS-72B-DPO) for more details on the model.
16
+ ## Use with mlx
17
+
18
+ ```bash
19
+ pip install -U mlx-vlm
20
+ ```
21
+
22
+ ```bash
23
+ python -m mlx_vlm.generate --model mlx-community/UI-TARS-72B-DPO-bf16 --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>
24
+ ```
added_tokens.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": false,
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "Qwen2VLForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bad_words_ids": null,
9
+ "begin_suppress_tokens": null,
10
+ "bos_token_id": 151643,
11
+ "chunk_size_feed_forward": 0,
12
+ "cross_attention_hidden_size": null,
13
+ "decoder_start_token_id": null,
14
+ "diversity_penalty": 0.0,
15
+ "do_sample": false,
16
+ "early_stopping": false,
17
+ "encoder_no_repeat_ngram_size": 0,
18
+ "eos_token_id": 151645,
19
+ "exponential_decay_length_penalty": null,
20
+ "finetuning_task": null,
21
+ "forced_bos_token_id": null,
22
+ "forced_eos_token_id": null,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 8192,
25
+ "id2label": {
26
+ "0": "LABEL_0",
27
+ "1": "LABEL_1"
28
+ },
29
+ "image_token_id": 151655,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 29568,
32
+ "is_decoder": false,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "length_penalty": 1.0,
39
+ "max_length": 20,
40
+ "max_position_embeddings": 32768,
41
+ "max_window_layers": 80,
42
+ "min_length": 0,
43
+ "model_type": "qwen2_vl",
44
+ "no_repeat_ngram_size": 0,
45
+ "num_attention_heads": 64,
46
+ "num_beam_groups": 1,
47
+ "num_beams": 1,
48
+ "num_hidden_layers": 80,
49
+ "num_key_value_heads": 8,
50
+ "num_return_sequences": 1,
51
+ "output_attentions": false,
52
+ "output_hidden_states": false,
53
+ "output_scores": false,
54
+ "pad_token_id": null,
55
+ "prefix": null,
56
+ "problem_type": null,
57
+ "pruned_heads": {},
58
+ "remove_invalid_values": false,
59
+ "repetition_penalty": 1.0,
60
+ "return_dict": true,
61
+ "return_dict_in_generate": false,
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": {
64
+ "type": "default",
65
+ "mrope_section": [
66
+ 16,
67
+ 24,
68
+ 24
69
+ ],
70
+ "rope_type": "default"
71
+ },
72
+ "rope_theta": 1000000.0,
73
+ "sep_token_id": null,
74
+ "sliding_window": 32768,
75
+ "suppress_tokens": null,
76
+ "task_specific_params": null,
77
+ "temperature": 1.0,
78
+ "tf_legacy_loss": false,
79
+ "tie_encoder_decoder": false,
80
+ "tie_word_embeddings": false,
81
+ "tokenizer_class": null,
82
+ "top_k": 50,
83
+ "top_p": 1.0,
84
+ "torch_dtype": "bfloat16",
85
+ "torchscript": false,
86
+ "transformers_version": "4.49.0",
87
+ "typical_p": 1.0,
88
+ "use_bfloat16": false,
89
+ "use_cache": true,
90
+ "use_sliding_window": false,
91
+ "video_token_id": 151656,
92
+ "vision_config": {
93
+ "return_dict": true,
94
+ "output_hidden_states": false,
95
+ "output_attentions": false,
96
+ "torchscript": false,
97
+ "torch_dtype": null,
98
+ "use_bfloat16": false,
99
+ "tf_legacy_loss": false,
100
+ "pruned_heads": {},
101
+ "tie_word_embeddings": true,
102
+ "chunk_size_feed_forward": 0,
103
+ "is_encoder_decoder": false,
104
+ "is_decoder": false,
105
+ "cross_attention_hidden_size": null,
106
+ "add_cross_attention": false,
107
+ "tie_encoder_decoder": false,
108
+ "max_length": 20,
109
+ "min_length": 0,
110
+ "do_sample": false,
111
+ "early_stopping": false,
112
+ "num_beams": 1,
113
+ "num_beam_groups": 1,
114
+ "diversity_penalty": 0.0,
115
+ "temperature": 1.0,
116
+ "top_k": 50,
117
+ "top_p": 1.0,
118
+ "typical_p": 1.0,
119
+ "repetition_penalty": 1.0,
120
+ "length_penalty": 1.0,
121
+ "no_repeat_ngram_size": 0,
122
+ "encoder_no_repeat_ngram_size": 0,
123
+ "bad_words_ids": null,
124
+ "num_return_sequences": 1,
125
+ "output_scores": false,
126
+ "return_dict_in_generate": false,
127
+ "forced_bos_token_id": null,
128
+ "forced_eos_token_id": null,
129
+ "remove_invalid_values": false,
130
+ "exponential_decay_length_penalty": null,
131
+ "suppress_tokens": null,
132
+ "begin_suppress_tokens": null,
133
+ "architectures": null,
134
+ "finetuning_task": null,
135
+ "id2label": {
136
+ "0": "LABEL_0",
137
+ "1": "LABEL_1"
138
+ },
139
+ "label2id": {
140
+ "LABEL_0": 0,
141
+ "LABEL_1": 1
142
+ },
143
+ "tokenizer_class": null,
144
+ "prefix": null,
145
+ "bos_token_id": null,
146
+ "pad_token_id": null,
147
+ "eos_token_id": null,
148
+ "sep_token_id": null,
149
+ "decoder_start_token_id": null,
150
+ "task_specific_params": null,
151
+ "problem_type": null,
152
+ "_name_or_path": "",
153
+ "_attn_implementation_autoset": false,
154
+ "in_chans": 3,
155
+ "spatial_patch_size": 14,
156
+ "depth": 32,
157
+ "embed_dim": 1280,
158
+ "hidden_size": 8192,
159
+ "hidden_act": "quick_gelu",
160
+ "mlp_ratio": 4,
161
+ "num_heads": 16,
162
+ "in_channels": 3,
163
+ "patch_size": 14,
164
+ "spatial_merge_size": 2,
165
+ "temporal_patch_size": 2,
166
+ "model_type": "qwen2_vl"
167
+ },
168
+ "vision_end_token_id": 151653,
169
+ "vision_start_token_id": 151652,
170
+ "vision_token_id": 151654,
171
+ "vocab_size": 152064
172
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61ce66198ea928d7c186da99d90cca129f39fde117c1e9a17ec2be1c4dbe7f20
3
+ size 5161069260
model-00002-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d80b75bb735776fc241706b8b8454b38578e64afd16ea41e6782747e304b48d2
3
+ size 5266113096
model-00003-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8ed60382603e1191419d6f020066c871ce186b6475d3ef3bf20eb4a0d0c5b24
3
+ size 5266113096
model-00004-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e328aad53eb70dbf089579d38dab3a1ff6d095a3ca40a69a7f959a4fd31981d
3
+ size 5266113096
model-00005-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1ccb490c2dd4b447af2a274aa99f5b650dc3d8d4cd109508e97dc67ca72552f
3
+ size 5266113133
model-00006-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec9cfcb73c9cfb501202eacb37c1fd368e248e4622bb68233dd085ccb5a52c01
3
+ size 5266113132
model-00007-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d8c8293006b45b0e709f6f6dc1f6128930ce7cd5becd09da7fe18ff32344adf
3
+ size 5266113128
model-00008-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ab3757fd827831a5fede1f1596fa8a1e9172d28747226905607ad9f7f6a853d
3
+ size 5266113100
model-00009-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aa459faf1f21407376047471e684cf889f333b8878d7c1975935a7a8275a5f1
3
+ size 5266113132
model-00010-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba083910e3617d0a442e9783c135ba9ce753f25db5bee7903ce2ed0405897cc4
3
+ size 5266113128
model-00011-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c8a26c7533c6e9622e62823daaee953382bc7dfea1f2adcbd9d29734cc3cff
3
+ size 5266113132
model-00012-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fcdee5ed2a4fb888800660b7956ac61d5416f6e8dd92664e2ff058067089dcc
3
+ size 5266113132
model-00013-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6572d358bf2ce974c318b56c1c059703ac4e2e6ee6346d519450fa3459854d48
3
+ size 5266113136
model-00014-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:369cc6046346bb356c95541a0f07d69ce673a58b43f659350ec2509c68d4a9bf
3
+ size 5266113132
model-00015-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22bfd2cb0e762a26d30e3f8e127e2cf28716cb1971ae4b1d5c76b6159c53843e
3
+ size 5266113130
model-00016-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2ed018b8ee813e892f20c6d418e959b6543cd969697a7d8de9f9104edd53c3a
3
+ size 5266113128
model-00017-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0bb11a1ace4a7cbb3579a7c72b5b4ace6a42be0b77a678ed46f18ec51184798
3
+ size 5266113136
model-00018-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d07fb9159a9912e59354f7c352da65bf4171ce5414de5865c7c646d7cda618
3
+ size 5266113128
model-00019-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:323b4fd4ccca79147752eae8a9d85a036bfba9547ce54ad6f3889b93bce6d8ed
3
+ size 5266113128
model-00020-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a116c609865a72e0ce7374c755d4069977891071dcac3c69c821fd48360c919
3
+ size 5266113096
model-00021-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8cf63477ef07d8587ec1c9c7c9ab452803e961345fb509d914fcee3a3949569
3
+ size 5266113130
model-00022-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da96ed39bc0d3b27b68ce88837ef1d2484dec85bab044bc6758a11459c11a1c0
3
+ size 5266113130
model-00023-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e398af9dd8ec99a6450f96eb9ede4eb08712b4a4cd638b85e61194869c8fa5e1
3
+ size 5266113136
model-00024-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a6f7ea741d855754c413a5392cb7e96d755485a9977998e31d156bd728e964d
3
+ size 5266113110
model-00025-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2256a626465fb3f31e6550fba179a08191640f62ec112051cc36aa034cfa03
3
+ size 5266113132
model-00026-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f30b8cbc76a7a375fd89d9f9022ac24c034681fe59b9c66e0568d15008a570c8
3
+ size 5266113128
model-00027-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cda3785ea226d06276bc3bdbfa2cc0f882ae6cc8aff2f580680aff8a6c206e3
3
+ size 5266113128
model-00028-of-00028.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50519b36cd5d682c69465e50d91168991fccee18fba3f70c4ccb913bdeb3d133
3
+ size 4731279516
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": true,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.48145466,
8
+ 0.4578275,
9
+ 0.40821073
10
+ ],
11
+ "image_processor_type": "Qwen2VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 2116800,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 2116800,
26
+ "shortest_edge": 3136
27
+ },
28
+ "temporal_patch_size": 2
29
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
3
+ size 11420371
tokenizer_config.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "additional_special_tokens": [
118
+ "<|im_start|>",
119
+ "<|im_end|>",
120
+ "<|object_ref_start|>",
121
+ "<|object_ref_end|>",
122
+ "<|box_start|>",
123
+ "<|box_end|>",
124
+ "<|quad_start|>",
125
+ "<|quad_end|>",
126
+ "<|vision_start|>",
127
+ "<|vision_end|>",
128
+ "<|vision_pad|>",
129
+ "<|image_pad|>",
130
+ "<|video_pad|>"
131
+ ],
132
+ "bos_token": null,
133
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{ message['role'].title() + ': ' + message['content'] | trim + eos_token + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant: ' }}{% endif %}",
134
+ "clean_up_tokenization_spaces": false,
135
+ "eos_token": "<|im_end|>",
136
+ "errors": "replace",
137
+ "extra_special_tokens": {},
138
+ "model_max_length": 32768,
139
+ "pad_token": "<|endoftext|>",
140
+ "padding_side": "right",
141
+ "processor_class": "Qwen2VLProcessor",
142
+ "split_special_tokens": false,
143
+ "tokenizer_class": "Qwen2Tokenizer",
144
+ "unk_token": null
145
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff