Instructions to use UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B") 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("UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B") model = AutoModelForMultimodalLM.from_pretrained("UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B", 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 UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B", "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/UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B
- SGLang
How to use UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B 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 "UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B" \ --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": "UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B", "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 "UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B" \ --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": "UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B", "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 UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B with Docker Model Runner:
docker model run hf.co/UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
This model, VLAA-Thinker-Qwen2VL-7B, is a vision-language model fine-tuned on the VLAA-Thinking dataset. As described in , it leverages a combination of supervised fine-tuning (SFT) and reinforcement learning (RL) to improve reasoning capabilities in LLMs. The model excels in multimodal reasoning tasks, achieving state-of-the-art performance on the OpenCompass Multimodal Reasoning Leaderboard as of April 7th, 2025.
π Project Page
β’
Arxiv
β’ π» Code
Both VLAA-Thinker-Qwen2.5-3B and VLAA-Thinker-Qwen2.5-7B achieve SOTA performance on OpenCompass Multimodal Reasoning Leaderboard as of April 7th, 2025.

Quick Start π
Inference
Run python inference.py. Note that our model is trained with a system prompt. Please ensure that it is included for inference.
Dataset Download
Run bash ./utils/download_dataset.sh. Specify the dataset root with absolute path. The dataset should be ordered as follows:
βββ VLAA-Thinking-SFT-126K.json
βββ VLAA-Thinking-GRPO-25K.json
βββ images
βββ allava_laion
βββ arxivqa
βββ chartqa
βββ clevr_math
βββ coco
β βββ train2017
βββ docvqa
βββ geoqa170k
βββ synthesis
βββ vg
β βββ VG_100K
β βββ VG_100K_2
βββ vizwiz
Training
Code coming soon!
(Rest of the README content can be kept as is)
- Downloads last month
- 49