Image-Text-to-Text
Transformers
Safetensors
qwen3_vl
qwen3-vl
vision-language
multilingual
ocr
grpo
conversational
Instructions to use DatasetMan/QGO-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DatasetMan/QGO-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="DatasetMan/QGO-8B") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("DatasetMan/QGO-8B") model = AutoModelForMultimodalLM.from_pretrained("DatasetMan/QGO-8B", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DatasetMan/QGO-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DatasetMan/QGO-8B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DatasetMan/QGO-8B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/DatasetMan/QGO-8B
- SGLang
How to use DatasetMan/QGO-8B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "DatasetMan/QGO-8B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DatasetMan/QGO-8B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "DatasetMan/QGO-8B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DatasetMan/QGO-8B", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use DatasetMan/QGO-8B with Docker Model Runner:
docker model run hf.co/DatasetMan/QGO-8B
|
Download README.md from DatasetMan/QGO-8B: direct link, hf CLI and curl.
- Browser
- Download file 4.44 kB
-
https://huggingface.co/DatasetMan/QGO-8B/resolve/main/README.md
- Command line
-
hf download hf://DatasetMan/QGO-8B/README.md
-
curl -L -o README.md https://huggingface.co/DatasetMan/QGO-8B/resolve/main/README.md
4.44 kB
| license: apache-2.0 | |
| library_name: transformers | |
| pipeline_tag: image-text-to-text | |
| base_model: Qwen/Qwen3-VL-8B-Thinking | |
| tags: | |
| - qwen3-vl | |
| - vision-language | |
| - multilingual | |
| - ocr | |
| - grpo | |
| datasets: | |
| - DatasetMan/PM4Bench-QGO-Train | |
| <div align="center"> | |
| # QGO-8B | |
| **OCR-centric reinforcement learning for multilingual LVLMs** | |
| [](https://little-bird-vodka.github.io/PM4Bench/paper-v3.html) | |
| [](https://little-bird-vodka.github.io/PM4Bench/) | |
| [](https://github.com/opendatalab/PM4Bench) | |
| [](https://huggingface.co/datasets/songjhPKU/PM4Bench) | |
| [](https://huggingface.co/datasets/DatasetMan/PM4Bench-QGO-Train) | |
| </div> | |
| ## Overview | |
| The paper [*Benchmarking and Boosting Multilingual Capabilities of LVLMs via | |
| OCR-Centric Reinforcement Learning*](https://little-bird-vodka.github.io/PM4Bench/paper-v3.html) | |
| introduces the strictly parallel PM4Bench benchmark and finds that OCR is a key | |
| source of cross-lingual performance gaps under vision-only input. QGO trains | |
| on fully synthesized OCR data with a dual reward for recognition accuracy and | |
| reasoning-preserving response structure. It improves average score on every | |
| PM4Bench task and setting and transfers gains to external multilingual OCR | |
| benchmarks. | |
| QGO-8B is the OCR-centric GRPO checkpoint derived from | |
| [`Qwen/Qwen3-VL-8B-Thinking`](https://huggingface.co/Qwen/Qwen3-VL-8B-Thinking). | |
| This repository contains the complete global-step-200 BF16 checkpoint used in | |
| the PM4Bench paper. | |
| ## Model details | |
| - Architecture: `Qwen3VLForConditionalGeneration` | |
| - Base model: `Qwen/Qwen3-VL-8B-Thinking` | |
| - Training method: GRPO | |
| - Released checkpoint: global step 200 | |
| - Weight format: safetensors, four BF16 shards | |
| - Indexed tensor bytes: 17,534,247,392 | |
| - License: Apache-2.0 | |
| - Tested Transformers version: 4.57.6 | |
| ## Usage | |
| ```python | |
| from transformers import AutoProcessor, Qwen3VLForConditionalGeneration | |
| model_id = "DatasetMan/QGO-8B" | |
| model = Qwen3VLForConditionalGeneration.from_pretrained( | |
| model_id, | |
| dtype="auto", | |
| device_map="auto", | |
| ) | |
| processor = AutoProcessor.from_pretrained(model_id) | |
| ``` | |
| The full BF16 weights are approximately 17.5 GB before runtime allocations. | |
| Plan GPU/CPU memory for weights, vision inputs, KV cache, and generation in | |
| addition to the checkpoint size. | |
| Use the base model's official chat template and greedy decoding for PM4Bench | |
| evaluation. Task prompts and evaluation code are provided in | |
| <https://github.com/opendatalab/PM4Bench>. | |
| ## Training | |
| The released data is available at | |
| <https://huggingface.co/datasets/DatasetMan/PM4Bench-QGO-Train>. The recipe | |
| uses 32 prompts and 8 rollouts per prompt (256 trajectories per step), AdamW | |
| with learning rate `1e-6`, BF16, and eight GPUs. | |
| ## PM4Bench evaluation | |
| | Model | MDUR trad. | MDUR vision | MIQA trad. | MIQA vision | MSOCR | MGUI | | |
| |---|---:|---:|---:|---:|---:|---:| | |
| | Qwen3-VL-8B-Thinking | 38.55 | 34.88 | 53.63 | 47.69 | 1.53 | 78.30 | | |
| | QGO-8B | 46.82 | 40.84 | 55.24 | 51.06 | 8.17 | 80.00 | | |
| These are the audited paper results. MDUR and MGUI are percentages, MIQA is | |
| the six-dimension judge score on a 10-100 scale, and MSOCR is on a 0-40 scale. | |
| ## Limitations | |
| QGO-8B targets multilingual OCR robustness. It inherits limitations and risks | |
| from the Qwen base model and is not guaranteed to improve every downstream | |
| task or language. Coordinate outputs, OCR transcriptions, and long-form | |
| reasoning should be validated before use in consequential applications. | |
| ## Cite Us | |
| <pre><code class="language-bibtex"> | |
| @misc{gao2026benchmarkingboostingmultilingualcapabilities, | |
| title={Benchmarking and Boosting Multilingual Capabilities of LVLMs via OCR-Centric Reinforcement Learning}, | |
| author={Junyuan Gao and Jiahe Song and Jiang Wu and Runchuan Zhu and Guanlin Shen and Shasha Wang and Xingjian Wei and Haote Yang and Weijia Li and Bin Wang and Lijun Wu and Conghui He}, | |
| year={2026}, | |
| eprint={2503.18484}, | |
| archivePrefix={arXiv}, | |
| primaryClass={cs.CV}, | |
| url={https://arxiv.org/abs/2503.18484v3}, | |
| } | |
| </code></pre> | |