From 03412fbc67bca5f67e6fe11c0250e317a848458d Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 25 Jul 2026 07:11:05 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: opendatalab/MinerU2.5-Pro-2605-1.2B Source: Original Platform --- .gitattributes | 52 +++++++ README.md | 251 +++++++++++++++++++++++++++++++++ added_tokens.json | 33 +++++ chat_template.jinja | 7 + config.json | 120 ++++++++++++++++ configuration.json | 1 + generation_config.json | 13 ++ merges.txt | 3 + model.safetensors | 3 + preprocessor_config.json | 11 ++ special_tokens_map.json | 48 +++++++ tokenizer.json | 3 + tokenizer_config.json | 297 +++++++++++++++++++++++++++++++++++++++ vocab.json | 3 + 14 files changed, 845 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 added_tokens.json create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 merges.txt create mode 100644 model.safetensors create mode 100644 preprocessor_config.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 vocab.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f413a51 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,52 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..c80aa17 --- /dev/null +++ b/README.md @@ -0,0 +1,251 @@ +--- +license: apache-2.0 +language: +- zh +- en +pipeline_tag: image-text-to-text +library_name: transformers +--- + + +
+ +

+ +

+ +

+MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale +

+ +

+ Tech Report + HuggingFace + ModelScope +

+
+ +--- + +

+ Image +

+ +### News 🚀🚀 + + 2026.05.21 🎉🎉 We are pleased to announce the release of MinerU2.5-Pro-2605, an updated version of our model. + + - **Enhanced Layout Detection** + To address the category misclassification issues observed in the 2604 version during layout detection, we conducted a comprehensive data cleaning process. This has substantially reduced category errors in layout detection. Notably, the missed detection rate for the `image_block` category has been significantly reduced. + + - **Improved Image Analysis** + To overcome the limitations of the 2604 version in image analysis, we constructed a large-scale training dataset for this task. As a result, the 2605 version demonstrates markedly enhanced recognition capabilities across a wide range of charts, flowcharts, and even seals. + + - **Comparable Performance on OmniDocBench** + The 2605 version primarily focuses on enhancing user experience, with performance metrics showing only marginal differences compared to the 2604 version. A detailed comparison of the metrics is presented below: + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
MinerU2.5-Pro-2605 vs. MinerU2.5-Pro-2604 on OmniDocBench (v1.6_full)
Model VersionOverall↑TextEdit↓FormulaCDM↑TableTEDS↑TableTEDS-S↑Read OrderEdit↓
MinerU2.5-Pro-260595.720.03697.1593.6296.010.123
MinerU2.5-Pro-260495.690.03697.2993.4295.920.120
+ + +### 🏆 Unmatched SOTA Performance +**MinerU2.5-Pro** is our latest document parsing model (PDF-to-Markdown) that establishes a new industry standard. By focusing entirely on data engineering without altering the original 1.2B-parameter architecture, it delivers exceptional results across the board: + +**1. Defeating Leading Models on OmniDocBench v1.6** +On the newly proposed, highly rigorous OmniDocBench v1.6, MinerU2.5-Pro achieves the absolute **SOTA overall score of 95.69**. It comprehensively outperforms both top-tier specialized OCR models (**GLM-OCR, PaddleOCR-VL-1.5**) and massive frontier VLMs (**Gemini 3 Pro, Qwen3-VL-235B**). + +**2. Massive Leap from MinerU 2.5 via Data Engineering** +Compared to the previous MinerU 2.5 baseline, the overall score skyrocketed from **92.98 to 95.69**. This breakthrough was achieved not by scaling model parameters, but through meticulous data engineering—drastically expanding data scale, enriching distribution and difficulty diversity, and systematically elevating annotation quality. + +**3. Exceptional Modality-Specific Breakthroughs** +* 📊 **Table Parsing:** Evaluated across 5 diverse table benchmarks, MinerU2.5-Pro dominates the leaderboard. It outperforms the 2nd place model by **1.39 points** and surpasses the original MinerU by **3.06 points** (with Table TEDS jumping specifically by **+5.54** on OmniDocBench). +* 🧮 **Formulas & Text:** Achieves SOTA levels with Dense Formula parsing (CDM) reaching **97.29** (+1.70), and Text Edit Distance dropping to an industry-best **0.036**. + +**4. ✨ New Practical Capabilities** +Beyond metric improvements, MinerU2.5-Pro now natively supports: **Image & Chart Parsing**, **Truncated Paragraph Merging**, **Cross-Page Table Merging** and **In-Table Image Recognition**. + +--- + +### 💡 How We Achieved It: The Data Engine +Current SOTA models (regardless of architecture) consistently fail on the same set of complex layouts. We realized the true bottleneck is **training data deficiency and annotation noise**. To fix this, we built a novel Data Engine: + +1. **Difficulty & Diversity-Aware Scaling:** We expanded the training corpus from under 10M to **65.5M pages**, heavily targeting long-tail hard samples while controlling distribution shifts. +2. **Solving the "Annotation Paradox":** Complex tables and dense formulas usually suffer from noisy automatic labels. We generated ultra-reliable annotations using **Cross-Model Consistency Verification (CMCV)** and an iterative **Judge-and-Refine** pipeline. +3. **3-Stage Progressive Training:** We maximized data utility by matching data quality tiers to a structured training pipeline: Large-scale Pre-training ➡️ High-quality Hard-Sample Fine-Tuning ➡️ GRPO Format Alignment. + +**Bottom Line:** MinerU2.5-Pro proves that systematic data engineering is the ultimate lever for document parsing, providing the most accurate structural extraction available today for LLM data pipelines and advanced RAG systems. + + + +# 1. Quick Start +For convenience, we provide `mineru-vl-utils`, a Python package that simplifies the process of sending requests and handling responses from MinerU2.5-Pro Vision-Language Model. Here we give some examples to use MinerU2.5-Pro. For more information and usages, please refer to [mineru-vl-utils](https://github.com/opendatalab/mineru-vl-utils/tree/main). + +📌 We strongly recommend using vllm for inference, as the `vllm-async-engine` can achieve a concurrent inference speed of **2.12 fps** on one A100. + +## 1.1. Install packages +```bash +# For `transformers` backend +pip install "mineru-vl-utils[transformers]" +# For `vllm-engine` and `vllm-async-engine` backend +pip install "mineru-vl-utils[vllm]" +``` + +## 1.2. `transformers` Example + +```python +from transformers import AutoProcessor, Qwen2VLForConditionalGeneration +from PIL import Image +from mineru_vl_utils import MinerUClient + +# for transformers>=4.56.0 +model = Qwen2VLForConditionalGeneration.from_pretrained( + "opendatalab/MinerU2.5-Pro-2605-1.2B", dtype="auto", device_map="auto" +) + +processor = AutoProcessor.from_pretrained( + "opendatalab/MinerU2.5-Pro-2605-1.2B", use_fast=True +) + +client = MinerUClient( + backend="transformers", model=model, processor=processor, + image_analysis=False # default False, set True to enable image/chart analysis +) + +print(client.two_step_extract(Image.open("/path/to/page.png"))) +``` + +## 1.3. `vllm-engine` Example (Recommended!) + +```python +from vllm import LLM +from PIL import Image +from mineru_vl_utils import MinerUClient +from mineru_vl_utils import MinerULogitsProcessor # if vllm>=0.10.1 + +llm = LLM( + model="opendatalab/MinerU2.5-Pro-2605-1.2B", + logits_processors=[MinerULogitsProcessor] # if vllm>=0.10.1 +) + +client = MinerUClient( + backend="vllm-engine", vllm_llm=llm, + image_analysis=False # default False, set True to enable image/chart analysis +) + +print(client.two_step_extract(Image.open("/path/to/page.png"))) +``` + +## 1.4. JSON result to Markdown (enable truncated paragraph merging) + +```python +from mineru_vl_utils.post_process import json2md + +# ... omit client initialize +content_list = client.two_step_extract(Image.open("path/to/page.png")) +md_res = json2md(content_list) +``` + +🚧 Cross-Page Table Merging: Currently under integration. Stay tuned! + + +# 2. Performance +## 2.1. End-to-End Document Parsing on OmniDocBench v1.6 +

+ Image +

+ +## 2.2. Text Recognition +

+ Image +

+ +## 2.3. Formula Recognition +

+ Image +

+ +## 2.4. Table Recognition +

+ Image +

+ +# 3. Showcase +## 3.1. Basic Parsing Capability + +

+ Image +

+ +

+ Image +

+ +

+ Image +

+ +## 3.2. Extra Supported Features +

+ Image +

+ +

+ Image +

+ +

+ Image +

+ +

+ Image +

+ + +# 4. Acknowledgement & Citation +We would like to thank [Qwen Team](https://github.com/QwenLM), [vLLM](https://github.com/vllm-project/vllm), [OmniDocBench](https://github.com/opendatalab/OmniDocBench), [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR), [UniMERNet](https://github.com/opendatalab/UniMERNet), [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO) for providing valuable code and models. We also appreciate everyone's contribution to this open-source project! + +If you find our work useful in your research, please consider giving a star ⭐ and citation 📝 : +```BibTeX +@misc{wang2026mineru25propushinglimitsdatacentric, + title={MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale}, + author={Bin, Wang and Tianyao, He and Linke, Ouyang and Fan, Wu and Zhiyuan, Zhao and Tao, Chu and Yuan, Qu and Zhenjiang, Jin and Weijun, Zeng and Ziyang, Miao and Bangrui, Xu and Junbo, Niu and others}, + year={2026}, + eprint={2604.04771}, + archivePrefix={arXiv}, + primaryClass={cs.CV}, + url={https://arxiv.org/abs/2604.04771}, +} +``` \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..d9604a3 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,33 @@ +{ + "": 151661, + "": 151662, + "": 151663, + "": 151664, + "": 151667, + "": 151665, + "": 151666, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|md_end|>": 151660, + "<|md_start|>": 151659, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|paratext|>": 151673, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|ref_end|>": 151658, + "<|ref_start|>": 151657, + "<|rotate_down|>": 151669, + "<|rotate_left|>": 151670, + "<|rotate_right|>": 151671, + "<|rotate_up|>": 151668, + "<|txt_contd|>": 151672, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..6c22663 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,7 @@ +{% 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 +You are a helpful assistant.<|im_end|> +{% endif %}<|im_start|>{{ message['role'] }} +{% if message['content'] is string %}{{ message['content'] }}<|im_end|> +{% 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|> +{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant +{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..c6bf7cf --- /dev/null +++ b/config.json @@ -0,0 +1,120 @@ +{ + "architectures": [ + "Qwen2VLForConditionalGeneration" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 896, + "image_token_id": 151655, + "initializer_range": 0.02, + "intermediate_size": 4864, + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2_vl", + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "mrope_section": [ + 8, + 12, + 12 + ], + "rope_type": "default", + "type": "default" + }, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "text_config": { + "architectures": [ + "Qwen2VLForConditionalGeneration" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 8192, + "max_window_layers": 24, + "model_type": "qwen2_vl", + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "mrope_section": [ + 8, + 12, + 12 + ], + "rope_type": "default", + "type": "default" + }, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": false, + "use_sliding_window": false, + "vision_token_id": 151654, + "vocab_size": 151936 + }, + "transformers_version": "4.57.2", + "use_cache": true, + "use_sliding_window": false, + "video_token_id": 151656, + "vision_config": { + "depth": 32, + "dtype": "bfloat16", + "embed_dim": 1280, + "hidden_act": "quick_gelu", + "hidden_size": 896, + "in_channels": 3, + "in_chans": 3, + "initializer_range": 0.02, + "mlp_ratio": 4, + "model_type": "qwen2_vl", + "num_heads": 16, + "pad_token_id": 151643, + "patch_size": 14, + "spatial_merge_size": 2, + "spatial_patch_size": 14, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652, + "vision_token_id": 151654, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..3ddf3e3 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework":"Pytorch","task":"document-understanding"} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..0fd0c93 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.01, + "top_k": 1, + "top_p": 0.001, + "transformers_version": "4.57.2" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..f9af43d --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abf8681ca63b8dec7b67de257af47b821f179442f72998d0696ae2ed9232a5f0 +size 2312126640 diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..3973ad8 --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,11 @@ +{ + "min_pixels": 50176, + "max_pixels": 1605632, + "patch_size": 14, + "temporal_patch_size": 2, + "merge_size": 2, + "image_mean": [0.48145466, 0.4578275, 0.40821073], + "image_std": [0.26862954, 0.26130258, 0.27577711], + "image_processor_type": "Qwen2VLImageProcessor", + "processor_class": "Qwen2VLProcessor" +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..3446fd1 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,48 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>", + "<|ref_start|>", + "<|ref_end|>", + "<|md_start|>", + "<|md_end|>", + "", + "", + "", + "", + "", + "", + "", + "<|rotate_up|>", + "<|rotate_down|>", + "<|rotate_left|>", + "<|rotate_right|>", + "<|txt_contd|>", + "<|paratext|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..5baa74d --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dceac5fc54a795ee7570d17902b47bd05412dc2afa62bdf325c3f97fcb5b87fe +size 11423550 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..0bedcd9 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,297 @@ +{ + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "<|ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151658": { + "content": "<|ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151659": { + "content": "<|md_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151660": { + "content": "<|md_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151661": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151662": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151663": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151664": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151668": { + "content": "<|rotate_up|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151669": { + "content": "<|rotate_down|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151670": { + "content": "<|rotate_left|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151671": { + "content": "<|rotate_right|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151672": { + "content": "<|txt_contd|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151673": { + "content": "<|paratext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>", + "<|ref_start|>", + "<|ref_end|>", + "<|md_start|>", + "<|md_end|>", + "", + "", + "", + "", + "", + "", + "", + "<|rotate_up|>", + "<|rotate_down|>", + "<|rotate_left|>", + "<|rotate_right|>", + "<|txt_contd|>", + "<|paratext|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 16384, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "processor_class": "Qwen2VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833