Image-Text-to-Text
Transformers
Safetensors
qwen3_5
vision-language
lookaway
visual-question-answering
conversational
Instructions to use pianzhikuang/VisAlloc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pianzhikuang/VisAlloc with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="pianzhikuang/VisAlloc") messages = [ { "role": "user", "content": [ {"type": "image", "url": "/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("pianzhikuang/VisAlloc") model = AutoModelForMultimodalLM.from_pretrained("pianzhikuang/VisAlloc", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "/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 pianzhikuang/VisAlloc with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "pianzhikuang/VisAlloc" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "pianzhikuang/VisAlloc", "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/pianzhikuang/VisAlloc
- SGLang
How to use pianzhikuang/VisAlloc 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 "pianzhikuang/VisAlloc" \ --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": "pianzhikuang/VisAlloc", "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 "pianzhikuang/VisAlloc" \ --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": "pianzhikuang/VisAlloc", "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 pianzhikuang/VisAlloc with Docker Model Runner:
docker model run hf.co/pianzhikuang/VisAlloc
Download evaluation/results.csv from pianzhikuang/VisAlloc: direct link, hf CLI and curl.
- Browser
- Download file 402 Bytes
-
/pianzhikuang/VisAlloc/resolve/main/evaluation/results.csv
- Command line
-
hf download hf://pianzhikuang/VisAlloc/evaluation/results.csv
-
curl -L -o results.csv /pianzhikuang/VisAlloc/resolve/main/evaluation/results.csv
402 Bytes
| benchmark,samples,scored_samples,metric,score_percent | |
| vstar,191,191,accuracy,83.25 | |
| zoombench,845,844,valid_subset_accuracy,58.29 | |
| hrbench-4k,800,800,accuracy,74.62 | |
| hrbench-8k,800,800,accuracy,72.25 | |
| mmvp,300,300,accuracy,78.00 | |
| cv-bench,2638,2638,mean_2D_3D_accuracy,74.77 | |
| mmstar,1500,1500,accuracy,62.20 | |
| pope,9000,9000,accuracy,89.03 | |
| mmvp,150,150,paired_accuracy,57.33 | |
| pope,9000,9000,f1,88.78 | |