Hugging Face's logo

FireRedTeam
/
ReMatch-3B

Safetensors
English
Chinese
qwen2_5_vl
Model card Files
xet
 Community
Excalibur-wsss commited on
Commit
f56cd6f
·
verified ·
1 Parent(s): a48e2df

Upload 12 files

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. README.md +151 -3
  3. adapter_config.json +185 -0
  4. adapter_model.safetensors +3 -0
  5. added_tokens.json +161 -0
  6. chat_template.json +3 -0
  7. config.json +67 -0
  8. merges.txt +0 -0
  9. preprocessor_config.json +31 -0
  10. special_tokens_map.json +31 -0
  11. tokenizer.json +3 -0
  12. tokenizer_config.json +1305 -0
  13. 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
README.md CHANGED
@@ -1,3 +1,151 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # ReMatch: Boosting Representation through Matching for Multimodal Retrieval
2
+
3
+ <p>
4
+ <a href="https://arxiv.org/abs/2511.19278"><img src="https://img.shields.io/badge/arXiv-2511.19278-b31b1b.svg" alt="arXiv"></a>
5
+ <a href="https://github.com/FireRedTeam/ReMatch"><img src="https://img.shields.io/badge/Code-ReMatch-green.svg" alt="Code"></a>
6
+ <a href="https://huggingface.co/FireRedTeam/ReMatch-3B"><img src="https://img.shields.io/badge/Model-ReMatch--3B-yellow.svg" alt="Model"></a>
7
+ </p>
8
+
9
+ This repository contains the official implementation of **ReMatch**, accepted to **CVPR 2026**.
10
+
11
+ ReMatch turns a multimodal large language model into a stronger multimodal retriever by adding a chat-style generative matching objective during training. The same MLLM learns to judge query-document relevance from both raw multimodal inputs and projected embeddings, complementing standard contrastive learning with instance-wise supervision on hard negatives. ReMatch also augments each input with multiple learnable representation tokens and fuses them into an efficient single-vector embedding for retrieval.
12
+
13
+ ## 👥 Authors
14
+
15
+ [Qianying Liu](https://scholar.google.com/citations?hl=zh-TW&user=QnMV-uYAAAAJ&view_op=list_works&sortby=pubdate)\*, Xiao Liang\*, Zhiqiang Zhang#, Yibo Chen, Xu Tang, Zhongfei Qing, Fengfan Zhou, Yao Hu, Paul Henderson
16
+
17
+ University of Glasgow, Xiaohongshu Inc., Huazhong University of Science and Technology
18
+
19
+ \* Equal contribution. # Project leader.
20
+
21
+ ## 🔍 Method
22
+
23
+ ![ReMatch framework](assets/rematch_framework.png)
24
+
25
+ ReMatch is built around two core ideas:
26
+
27
+ - **Query-Document Matching**: an additional autoregressive matching stage that predicts relevance from the query, document, and their projected embeddings.
28
+ - **Learnable Multi-Token Embeddings**: multiple learnable tokens capture fine-grained contextual signals; an orthogonality regularizer encourages complementary representations, and the fused output remains a standard dense embedding.
29
+
30
+ ## 🔥 News
31
+
32
+ - **2026-05**: ReMatch code, the **ReMatch-3B** checkpoint, and evaluation scripts are released.
33
+ - **2026-02**: ReMatch is accepted to **CVPR 2026**.
34
+ - **2025-11**: The ReMatch technical report is available on arXiv.
35
+
36
+ ## 🛠️ Installation
37
+
38
+ ```bash
39
+ conda create -n rematch python=3.10 -y
40
+ conda activate rematch
41
+ pip install -r requirements.txt
42
+ ```
43
+
44
+ `flash-attn` can be sensitive to CUDA, PyTorch, and compiler versions. If installation fails, install the wheel matching your environment from the official FlashAttention release instructions, then rerun the remaining dependencies.
45
+
46
+ ## 🤗 Checkpoints
47
+
48
+ We release **ReMatch-3B**, a Qwen2.5-VL-3B based checkpoint trained with the ReMatch recipe:
49
+
50
+ - [FireRedTeam/ReMatch-3B](https://huggingface.co/FireRedTeam/ReMatch-3B)
51
+
52
+ For local checkpoints, pass the base model through `--model_name` and the adapter/full checkpoint through `--checkpoint_path` when evaluating.
53
+
54
+ ## 🚀 Training
55
+
56
+ The public ReMatch-3B training entry point is:
57
+
58
+ ```bash
59
+ bash experiments/public/rematch/train-rematch-itm.sh
60
+ ```
61
+
62
+ Before training, download the mmE5 hard-negative MMEB training data from Hugging Face:
63
+
64
+ - [intfloat/mmE5-MMEB-hardneg](https://huggingface.co/datasets/intfloat/mmE5-MMEB-hardneg)
65
+
66
+ In addition to mmE5, please follow the original [VLM2Vec](https://github.com/TIGER-AI-Lab/VLM2Vec) data preparation instructions to download the corresponding MMEB training and evaluation data used by the public configs in this repository.
67
+
68
+ Then edit [experiments/public/rematch/train_image_mme5_hardneg.yaml](experiments/public/rematch/train_image_mme5_hardneg.yaml) and replace every `DATASET_BASE_PATH` with the directory that contains your `mmE5/` folder. The expected layout is:
69
+
70
+ ```text
71
+ DATASET_BASE_PATH/
72
+ └── mmE5/
73
+ └── mmE5-MMEB-hardneg/
74
+ ```
75
+
76
+ The default script trains a Qwen2.5-VL-3B based ReMatch model with LoRA, 16 learnable query tokens, residual average fusion, orthogonal regularization, and the matching objective enabled. You can override common paths without editing the script:
77
+
78
+ ```bash
79
+ EXP_DIR=/path/to/output \
80
+ CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
81
+ bash experiments/public/rematch/train-rematch-itm.sh
82
+ ```
83
+
84
+ ## 📊 Evaluation
85
+
86
+ Evaluation configs are under [experiments/public/eval](experiments/public/eval):
87
+
88
+ - [image.yaml](experiments/public/eval/image.yaml)
89
+
90
+ Please prepare the MMEB evaluation data following the original [VLM2Vec](https://github.com/TIGER-AI-Lab/VLM2Vec) instructions, then set `DATA_BASEDIR` to the directory containing the downloaded evaluation files.
91
+
92
+ > **Note:** Evaluation scores may vary slightly across environments, as different PyTorch, CUDA, and `flash-attn` versions can introduce small numerical differences.
93
+
94
+ For checkpoints produced by this repository, we recommend using `eval_all.py`. It reads the experiment name and automatically matches the evaluation configuration used by ReMatch, including backbone type, target-side instruction prefix, chat template, learnable query tokens, and residual embedding fusion. For example, an experiment name containing `Qwen2.5vl`, `TgtInstruction`, `Queries16`, `ResidualAvg`, and `ChatTemplate` will be evaluated with the corresponding `qwen2_5_vl`, target instruction, 16 learnable tokens, average residual fusion, and chat-template settings.
95
+
96
+ Evaluate one experiment checkpoint:
97
+
98
+ ```bash
99
+ DATA_BASEDIR=/path/to/vlm2vec_eval \
100
+ MODEL_BASEDIR=/path/to/training/outputs \
101
+ OUTPUT_BASEDIR=/path/to/eval/outputs \
102
+ MODALITIES="image" \
103
+ python eval_all.py \
104
+ --model_name Rematch_Qwen2.5vl_3B.image.autoresize.lora32.loraAlpha64.BS1024.IB64.GCq32p32NormTemp002.lr1e4.step3kwarm100.lrCosine.TgtInstruction.mmE5H1.Queries16.ResidualAvg.OrthTriu0.2.ChatTemplate.ITM.V1.Ratio0.1 \
105
+ --checkpoint_name checkpoint-2200
106
+ ```
107
+
108
+ If no arguments are provided, `eval_all.py` scans `outputs/<model_name>/<checkpoint_name>/`, evaluates every checkpoint directory, and writes summaries to:
109
+
110
+ ```text
111
+ outputs/evals/<model_name>/<checkpoint_name>/final_results.json
112
+ ```
113
+
114
+ For the released **ReMatch-3B** checkpoint, use `eval.py` directly and pass the matching ReMatch configuration explicitly:
115
+
116
+ ```bash
117
+ torchrun --nproc_per_node=8 --master_port=2277 eval.py \
118
+ --lora True \
119
+ --pooling eos \
120
+ --normalize true \
121
+ --tgt_prefix_instruction True \
122
+ --learnable_queries True \
123
+ --residual_embedding True \
124
+ --residual_embedding_method avg \
125
+ --enable_chat_template True \
126
+ --num_queries 16 \
127
+ --per_device_eval_batch_size 16 \
128
+ --model_backbone qwen2_5_vl \
129
+ --model_name ReMatch-3B-PATH \
130
+ --checkpoint_path ReMatch-3B-PATH \
131
+ --dataset_config experiments/public/eval/image.yaml \
132
+ --encode_output_path outputs/evals/ReMatch-3B/image \
133
+ --data_basedir /path/to/MMEB
134
+ ```
135
+
136
+ ## 🙏 Acknowledgements
137
+
138
+ This codebase is built on top of [VLM2Vec](https://github.com/TIGER-AI-Lab/VLM2Vec). We sincerely thank the VLM2Vec authors for releasing their training and evaluation infrastructure for massive multimodal embedding tasks.
139
+
140
+ We also thank the authors of Qwen2.5-VL, MMEB, and mmE5 for their open models, benchmarks, and data resources.
141
+
142
+ ## 📚 Citation
143
+
144
+ ```bibtex
145
+ @article{liu2025rematch,
146
+ title={ReMatch: Boosting Representation through Matching for Multimodal Retrieval},
147
+ author={Liu, Qianying and Liang, Xiao and Zhang, Zhiqiang and Chen, Yibo and Tang, Xu and Qing, Zhongfei and Zhou, Fengfan and Hu, Yao and Henderson, Paul},
148
+ journal={arXiv preprint arXiv:2511.19278},
149
+ year={2025}
150
+ }
151
+ ```
adapter_config.json ADDED
@@ -0,0 +1,185 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": {
4
+ "base_model_class": "Qwen2_5_VLForConditionalGeneration",
5
+ "parent_library": "src.model.vlm_backbone.qwen2_5_vl.modeling_qwen2_5_vl"
6
+ },
7
+ "base_model_name_or_path": "Qwen/Qwen2.5-VL-3B-Instruct",
8
+ "bias": "none",
9
+ "corda_config": null,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": false,
13
+ "inference_mode": true,
14
+ "init_lora_weights": "gaussian",
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 64,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.1,
22
+ "megatron_config": null,
23
+ "megatron_core": "megatron.core",
24
+ "modules_to_save": null,
25
+ "peft_type": "LORA",
26
+ "qalora_group_size": 16,
27
+ "r": 32,
28
+ "rank_pattern": {},
29
+ "revision": null,
30
+ "target_modules": [
31
+ "down_proj",
32
+ "qkv_proj",
33
+ "out_proj",
34
+ "q_proj",
35
+ "gate_up_proj",
36
+ "v_proj",
37
+ "k_proj",
38
+ "o_proj"
39
+ ],
40
+ "task_type": null,
41
+ "trainable_token_indices": {
42
+ "embed_tokens": [
43
+ 151665,
44
+ 151666,
45
+ 151667,
46
+ 151668,
47
+ 151669,
48
+ 151670,
49
+ 151671,
50
+ 151672,
51
+ 151673,
52
+ 151674,
53
+ 151675,
54
+ 151676,
55
+ 151677,
56
+ 151678,
57
+ 151679,
58
+ 151680,
59
+ 151681,
60
+ 151682,
61
+ 151683,
62
+ 151684,
63
+ 151685,
64
+ 151686,
65
+ 151687,
66
+ 151688,
67
+ 151689,
68
+ 151690,
69
+ 151691,
70
+ 151692,
71
+ 151693,
72
+ 151694,
73
+ 151695,
74
+ 151696,
75
+ 151697,
76
+ 151698,
77
+ 151699,
78
+ 151700,
79
+ 151701,
80
+ 151702,
81
+ 151703,
82
+ 151704,
83
+ 151705,
84
+ 151706,
85
+ 151707,
86
+ 151708,
87
+ 151709,
88
+ 151710,
89
+ 151711,
90
+ 151712,
91
+ 151713,
92
+ 151714,
93
+ 151715,
94
+ 151716,
95
+ 151717,
96
+ 151718,
97
+ 151719,
98
+ 151720,
99
+ 151721,
100
+ 151722,
101
+ 151723,
102
+ 151724,
103
+ 151725,
104
+ 151726,
105
+ 151727,
106
+ 151728,
107
+ 151729,
108
+ 151730,
109
+ 151731,
110
+ 151732,
111
+ 151733,
112
+ 151734,
113
+ 151735,
114
+ 151736,
115
+ 151737,
116
+ 151738,
117
+ 151739,
118
+ 151740,
119
+ 151741,
120
+ 151742,
121
+ 151743,
122
+ 151744,
123
+ 151745,
124
+ 151746,
125
+ 151747,
126
+ 151748,
127
+ 151749,
128
+ 151750,
129
+ 151751,
130
+ 151752,
131
+ 151753,
132
+ 151754,
133
+ 151755,
134
+ 151756,
135
+ 151757,
136
+ 151758,
137
+ 151759,
138
+ 151760,
139
+ 151761,
140
+ 151762,
141
+ 151763,
142
+ 151764,
143
+ 151765,
144
+ 151766,
145
+ 151767,
146
+ 151768,
147
+ 151769,
148
+ 151770,
149
+ 151771,
150
+ 151772,
151
+ 151773,
152
+ 151774,
153
+ 151775,
154
+ 151776,
155
+ 151777,
156
+ 151778,
157
+ 151779,
158
+ 151780,
159
+ 151781,
160
+ 151782,
161
+ 151783,
162
+ 151784,
163
+ 151785,
164
+ 151786,
165
+ 151787,
166
+ 151788,
167
+ 151789,
168
+ 151790,
169
+ 151791,
170
+ 151792,
171
+ 151793,
172
+ 151794,
173
+ 151795,
174
+ 151796,
175
+ 151797,
176
+ 151798,
177
+ 151799,
178
+ 151800,
179
+ 151801
180
+ ]
181
+ },
182
+ "use_dora": true,
183
+ "use_qalora": false,
184
+ "use_rslora": false
185
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebec929a8b201ecbfb0568dffa887f402fcec88b70be7ae2ba6d99b8e142b1b5
3
+ size 140726872
added_tokens.json ADDED
@@ -0,0 +1,161 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</DOC>": 151688,
3
+ "</QUERY>": 151686,
4
+ "</answer>": 151668,
5
+ "</tool_call>": 151658,
6
+ "<DOC>": 151687,
7
+ "<QUERY>": 151685,
8
+ "<answer>": 151667,
9
+ "<feat_00000>": 151669,
10
+ "<feat_00001>": 151670,
11
+ "<feat_00002>": 151671,
12
+ "<feat_00003>": 151672,
13
+ "<feat_00004>": 151673,
14
+ "<feat_00005>": 151674,
15
+ "<feat_00006>": 151675,
16
+ "<feat_00007>": 151676,
17
+ "<feat_00008>": 151677,
18
+ "<feat_00009>": 151678,
19
+ "<feat_00010>": 151679,
20
+ "<feat_00011>": 151680,
21
+ "<feat_00012>": 151681,
22
+ "<feat_00013>": 151682,
23
+ "<feat_00014>": 151683,
24
+ "<feat_00015>": 151684,
25
+ "<feat_00016>": 151690,
26
+ "<feat_00017>": 151691,
27
+ "<feat_00018>": 151692,
28
+ "<feat_00019>": 151693,
29
+ "<feat_00020>": 151694,
30
+ "<feat_00021>": 151695,
31
+ "<feat_00022>": 151696,
32
+ "<feat_00023>": 151697,
33
+ "<feat_00024>": 151698,
34
+ "<feat_00025>": 151699,
35
+ "<feat_00026>": 151700,
36
+ "<feat_00027>": 151701,
37
+ "<feat_00028>": 151702,
38
+ "<feat_00029>": 151703,
39
+ "<feat_00030>": 151704,
40
+ "<feat_00031>": 151705,
41
+ "<feat_00032>": 151706,
42
+ "<feat_00033>": 151707,
43
+ "<feat_00034>": 151708,
44
+ "<feat_00035>": 151709,
45
+ "<feat_00036>": 151710,
46
+ "<feat_00037>": 151711,
47
+ "<feat_00038>": 151712,
48
+ "<feat_00039>": 151713,
49
+ "<feat_00040>": 151714,
50
+ "<feat_00041>": 151715,
51
+ "<feat_00042>": 151716,
52
+ "<feat_00043>": 151717,
53
+ "<feat_00044>": 151718,
54
+ "<feat_00045>": 151719,
55
+ "<feat_00046>": 151720,
56
+ "<feat_00047>": 151721,
57
+ "<feat_00048>": 151722,
58
+ "<feat_00049>": 151723,
59
+ "<feat_00050>": 151724,
60
+ "<feat_00051>": 151725,
61
+ "<feat_00052>": 151726,
62
+ "<feat_00053>": 151727,
63
+ "<feat_00054>": 151728,
64
+ "<feat_00055>": 151729,
65
+ "<feat_00056>": 151730,
66
+ "<feat_00057>": 151731,
67
+ "<feat_00058>": 151732,
68
+ "<feat_00059>": 151733,
69
+ "<feat_00060>": 151734,
70
+ "<feat_00061>": 151735,
71
+ "<feat_00062>": 151736,
72
+ "<feat_00063>": 151737,
73
+ "<feat_00064>": 151738,
74
+ "<feat_00065>": 151739,
75
+ "<feat_00066>": 151740,
76
+ "<feat_00067>": 151741,
77
+ "<feat_00068>": 151742,
78
+ "<feat_00069>": 151743,
79
+ "<feat_00070>": 151744,
80
+ "<feat_00071>": 151745,
81
+ "<feat_00072>": 151746,
82
+ "<feat_00073>": 151747,
83
+ "<feat_00074>": 151748,
84
+ "<feat_00075>": 151749,
85
+ "<feat_00076>": 151750,
86
+ "<feat_00077>": 151751,
87
+ "<feat_00078>": 151752,
88
+ "<feat_00079>": 151753,
89
+ "<feat_00080>": 151754,
90
+ "<feat_00081>": 151755,
91
+ "<feat_00082>": 151756,
92
+ "<feat_00083>": 151757,
93
+ "<feat_00084>": 151758,
94
+ "<feat_00085>": 151759,
95
+ "<feat_00086>": 151760,
96
+ "<feat_00087>": 151761,
97
+ "<feat_00088>": 151762,
98
+ "<feat_00089>": 151763,
99
+ "<feat_00090>": 151764,
100
+ "<feat_00091>": 151765,
101
+ "<feat_00092>": 151766,
102
+ "<feat_00093>": 151767,
103
+ "<feat_00094>": 151768,
104
+ "<feat_00095>": 151769,
105
+ "<feat_00096>": 151770,
106
+ "<feat_00097>": 151771,
107
+ "<feat_00098>": 151772,
108
+ "<feat_00099>": 151773,
109
+ "<feat_00100>": 151774,
110
+ "<feat_00101>": 151775,
111
+ "<feat_00102>": 151776,
112
+ "<feat_00103>": 151777,
113
+ "<feat_00104>": 151778,
114
+ "<feat_00105>": 151779,
115
+ "<feat_00106>": 151780,
116
+ "<feat_00107>": 151781,
117
+ "<feat_00108>": 151782,
118
+ "<feat_00109>": 151783,
119
+ "<feat_00110>": 151784,
120
+ "<feat_00111>": 151785,
121
+ "<feat_00112>": 151786,
122
+ "<feat_00113>": 151787,
123
+ "<feat_00114>": 151788,
124
+ "<feat_00115>": 151789,
125
+ "<feat_00116>": 151790,
126
+ "<feat_00117>": 151791,
127
+ "<feat_00118>": 151792,
128
+ "<feat_00119>": 151793,
129
+ "<feat_00120>": 151794,
130
+ "<feat_00121>": 151795,
131
+ "<feat_00122>": 151796,
132
+ "<feat_00123>": 151797,
133
+ "<feat_00124>": 151798,
134
+ "<feat_00125>": 151799,
135
+ "<feat_00126>": 151800,
136
+ "<feat_00127>": 151801,
137
+ "<tool_call>": 151657,
138
+ "<|box_end|>": 151649,
139
+ "<|box_start|>": 151648,
140
+ "<|endoftext|>": 151643,
141
+ "<|feat_end|>": 151666,
142
+ "<|feat_pad|>": 151689,
143
+ "<|feat_start|>": 151665,
144
+ "<|file_sep|>": 151664,
145
+ "<|fim_middle|>": 151660,
146
+ "<|fim_pad|>": 151662,
147
+ "<|fim_prefix|>": 151659,
148
+ "<|fim_suffix|>": 151661,
149
+ "<|im_end|>": 151645,
150
+ "<|im_start|>": 151644,
151
+ "<|image_pad|>": 151655,
152
+ "<|object_ref_end|>": 151647,
153
+ "<|object_ref_start|>": 151646,
154
+ "<|quad_end|>": 151651,
155
+ "<|quad_start|>": 151650,
156
+ "<|repo_name|>": 151663,
157
+ "<|video_pad|>": 151656,
158
+ "<|vision_end|>": 151653,
159
+ "<|vision_pad|>": 151654,
160
+ "<|vision_start|>": 151652
161
+ }
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 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Qwen2_5_VLForConditionalGeneration"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 2048,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 128000,
15
+ "max_window_layers": 70,
16
+ "model_type": "qwen2_5_vl",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 36,
19
+ "num_key_value_heads": 2,
20
+ "padding_side": "left",
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": {
23
+ "mrope_section": [
24
+ 16,
25
+ 24,
26
+ 24
27
+ ],
28
+ "rope_type": "default",
29
+ "type": "default"
30
+ },
31
+ "rope_theta": 1000000.0,
32
+ "sliding_window": 32768,
33
+ "tie_word_embeddings": true,
34
+ "torch_dtype": "bfloat16",
35
+ "transformers_version": "4.51.2",
36
+ "use_cache": false,
37
+ "use_sliding_window": false,
38
+ "video_token_id": 151656,
39
+ "vision_config": {
40
+ "depth": 32,
41
+ "fullatt_block_indexes": [
42
+ 7,
43
+ 15,
44
+ 23,
45
+ 31
46
+ ],
47
+ "hidden_act": "silu",
48
+ "hidden_size": 1280,
49
+ "in_channels": 3,
50
+ "in_chans": 3,
51
+ "intermediate_size": 3420,
52
+ "model_type": "qwen2_5_vl",
53
+ "num_heads": 16,
54
+ "out_hidden_size": 2048,
55
+ "patch_size": 14,
56
+ "spatial_merge_size": 2,
57
+ "spatial_patch_size": 14,
58
+ "temporal_patch_size": 2,
59
+ "tokens_per_second": 2,
60
+ "torch_dtype": "bfloat16",
61
+ "window_size": 112
62
+ },
63
+ "vision_end_token_id": 151653,
64
+ "vision_start_token_id": 151652,
65
+ "vision_token_id": 151654,
66
+ "vocab_size": 151936
67
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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": "Qwen2_5_VLImageProcessor",
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "max_pixels": 1003520,
18
+ "merge_size": 2,
19
+ "min_pixels": 3136,
20
+ "patch_size": 14,
21
+ "processor_class": "Qwen2_5_VLProcessor",
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "longest_edge": 1003520,
26
+ "max_pixels": 1003520,
27
+ "min_pixels": 3136,
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 sha256:59fdd6a459b23feead073232b34adc989d40d3d6ca59c2187f8cb33daa7e5fef
3
+ size 11447762
tokenizer_config.json ADDED
@@ -0,0 +1,1305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<|feat_start|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|feat_end|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<answer>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "</answer>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "<feat_00000>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<feat_00001>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<feat_00002>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<feat_00003>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<feat_00004>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<feat_00005>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<feat_00006>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151676": {
270
+ "content": "<feat_00007>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "<feat_00008>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151678": {
286
+ "content": "<feat_00009>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151679": {
294
+ "content": "<feat_00010>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151680": {
302
+ "content": "<feat_00011>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151681": {
310
+ "content": "<feat_00012>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151682": {
318
+ "content": "<feat_00013>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151683": {
326
+ "content": "<feat_00014>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151684": {
334
+ "content": "<feat_00015>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151685": {
342
+ "content": "<QUERY>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151686": {
350
+ "content": "</QUERY>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151687": {
358
+ "content": "<DOC>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151688": {
366
+ "content": "</DOC>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151689": {
374
+ "content": "<|feat_pad|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151690": {
382
+ "content": "<feat_00016>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151691": {
390
+ "content": "<feat_00017>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151692": {
398
+ "content": "<feat_00018>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151693": {
406
+ "content": "<feat_00019>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151694": {
414
+ "content": "<feat_00020>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151695": {
422
+ "content": "<feat_00021>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151696": {
430
+ "content": "<feat_00022>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151697": {
438
+ "content": "<feat_00023>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151698": {
446
+ "content": "<feat_00024>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151699": {
454
+ "content": "<feat_00025>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151700": {
462
+ "content": "<feat_00026>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "151701": {
470
+ "content": "<feat_00027>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "151702": {
478
+ "content": "<feat_00028>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "151703": {
486
+ "content": "<feat_00029>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "151704": {
494
+ "content": "<feat_00030>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "151705": {
502
+ "content": "<feat_00031>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "151706": {
510
+ "content": "<feat_00032>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "151707": {
518
+ "content": "<feat_00033>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "151708": {
526
+ "content": "<feat_00034>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "151709": {
534
+ "content": "<feat_00035>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "151710": {
542
+ "content": "<feat_00036>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "151711": {
550
+ "content": "<feat_00037>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "151712": {
558
+ "content": "<feat_00038>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "151713": {
566
+ "content": "<feat_00039>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "151714": {
574
+ "content": "<feat_00040>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "151715": {
582
+ "content": "<feat_00041>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "151716": {
590
+ "content": "<feat_00042>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "151717": {
598
+ "content": "<feat_00043>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "151718": {
606
+ "content": "<feat_00044>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "151719": {
614
+ "content": "<feat_00045>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "151720": {
622
+ "content": "<feat_00046>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "151721": {
630
+ "content": "<feat_00047>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "151722": {
638
+ "content": "<feat_00048>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "151723": {
646
+ "content": "<feat_00049>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "151724": {
654
+ "content": "<feat_00050>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "151725": {
662
+ "content": "<feat_00051>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "151726": {
670
+ "content": "<feat_00052>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "151727": {
678
+ "content": "<feat_00053>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "151728": {
686
+ "content": "<feat_00054>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "151729": {
694
+ "content": "<feat_00055>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "151730": {
702
+ "content": "<feat_00056>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "151731": {
710
+ "content": "<feat_00057>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "151732": {
718
+ "content": "<feat_00058>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "151733": {
726
+ "content": "<feat_00059>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "151734": {
734
+ "content": "<feat_00060>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "151735": {
742
+ "content": "<feat_00061>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "151736": {
750
+ "content": "<feat_00062>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "151737": {
758
+ "content": "<feat_00063>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "151738": {
766
+ "content": "<feat_00064>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "151739": {
774
+ "content": "<feat_00065>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "151740": {
782
+ "content": "<feat_00066>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "151741": {
790
+ "content": "<feat_00067>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "151742": {
798
+ "content": "<feat_00068>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "151743": {
806
+ "content": "<feat_00069>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "151744": {
814
+ "content": "<feat_00070>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "151745": {
822
+ "content": "<feat_00071>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "151746": {
830
+ "content": "<feat_00072>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "151747": {
838
+ "content": "<feat_00073>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "151748": {
846
+ "content": "<feat_00074>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "151749": {
854
+ "content": "<feat_00075>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "151750": {
862
+ "content": "<feat_00076>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "151751": {
870
+ "content": "<feat_00077>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "151752": {
878
+ "content": "<feat_00078>",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "151753": {
886
+ "content": "<feat_00079>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "151754": {
894
+ "content": "<feat_00080>",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "151755": {
902
+ "content": "<feat_00081>",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "151756": {
910
+ "content": "<feat_00082>",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "151757": {
918
+ "content": "<feat_00083>",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "151758": {
926
+ "content": "<feat_00084>",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "151759": {
934
+ "content": "<feat_00085>",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "151760": {
942
+ "content": "<feat_00086>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "151761": {
950
+ "content": "<feat_00087>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "151762": {
958
+ "content": "<feat_00088>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "151763": {
966
+ "content": "<feat_00089>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "151764": {
974
+ "content": "<feat_00090>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "151765": {
982
+ "content": "<feat_00091>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "151766": {
990
+ "content": "<feat_00092>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "151767": {
998
+ "content": "<feat_00093>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "151768": {
1006
+ "content": "<feat_00094>",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "151769": {
1014
+ "content": "<feat_00095>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "151770": {
1022
+ "content": "<feat_00096>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "151771": {
1030
+ "content": "<feat_00097>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "151772": {
1038
+ "content": "<feat_00098>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "151773": {
1046
+ "content": "<feat_00099>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "151774": {
1054
+ "content": "<feat_00100>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "151775": {
1062
+ "content": "<feat_00101>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "151776": {
1070
+ "content": "<feat_00102>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "151777": {
1078
+ "content": "<feat_00103>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "151778": {
1086
+ "content": "<feat_00104>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "151779": {
1094
+ "content": "<feat_00105>",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "151780": {
1102
+ "content": "<feat_00106>",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "151781": {
1110
+ "content": "<feat_00107>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "151782": {
1118
+ "content": "<feat_00108>",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "151783": {
1126
+ "content": "<feat_00109>",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "151784": {
1134
+ "content": "<feat_00110>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "151785": {
1142
+ "content": "<feat_00111>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "151786": {
1150
+ "content": "<feat_00112>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "151787": {
1158
+ "content": "<feat_00113>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "151788": {
1166
+ "content": "<feat_00114>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "151789": {
1174
+ "content": "<feat_00115>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "151790": {
1182
+ "content": "<feat_00116>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "151791": {
1190
+ "content": "<feat_00117>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "151792": {
1198
+ "content": "<feat_00118>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "151793": {
1206
+ "content": "<feat_00119>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "151794": {
1214
+ "content": "<feat_00120>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "151795": {
1222
+ "content": "<feat_00121>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "151796": {
1230
+ "content": "<feat_00122>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "151797": {
1238
+ "content": "<feat_00123>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "151798": {
1246
+ "content": "<feat_00124>",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": true
1252
+ },
1253
+ "151799": {
1254
+ "content": "<feat_00125>",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": true
1260
+ },
1261
+ "151800": {
1262
+ "content": "<feat_00126>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "151801": {
1270
+ "content": "<feat_00127>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ }
1277
+ },
1278
+ "additional_special_tokens": [
1279
+ "<|im_start|>",
1280
+ "<|im_end|>",
1281
+ "<|object_ref_start|>",
1282
+ "<|object_ref_end|>",
1283
+ "<|box_start|>",
1284
+ "<|box_end|>",
1285
+ "<|quad_start|>",
1286
+ "<|quad_end|>",
1287
+ "<|vision_start|>",
1288
+ "<|vision_end|>",
1289
+ "<|vision_pad|>",
1290
+ "<|image_pad|>",
1291
+ "<|video_pad|>"
1292
+ ],
1293
+ "bos_token": null,
1294
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
1295
+ "clean_up_tokenization_spaces": false,
1296
+ "eos_token": "<|im_end|>",
1297
+ "errors": "replace",
1298
+ "extra_special_tokens": {},
1299
+ "model_max_length": 131072,
1300
+ "pad_token": "<|endoftext|>",
1301
+ "processor_class": "Qwen2_5_VLProcessor",
1302
+ "split_special_tokens": false,
1303
+ "tokenizer_class": "Qwen2Tokenizer",
1304
+ "unk_token": null
1305
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff