Instructions to use AZYoung/GC-Cap-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AZYoung/GC-Cap-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="AZYoung/GC-Cap-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("AZYoung/GC-Cap-8B") model = AutoModelForMultimodalLM.from_pretrained("AZYoung/GC-Cap-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 AZYoung/GC-Cap-8B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AZYoung/GC-Cap-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": "AZYoung/GC-Cap-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/AZYoung/GC-Cap-8B
- SGLang
How to use AZYoung/GC-Cap-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 "AZYoung/GC-Cap-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": "AZYoung/GC-Cap-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 "AZYoung/GC-Cap-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": "AZYoung/GC-Cap-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 AZYoung/GC-Cap-8B with Docker Model Runner:
docker model run hf.co/AZYoung/GC-Cap-8B
Academic access only
GC-Cap is released for non-commercial academic research. It is not offered to users in the European Union. Requests from European Union IP addresses are not accepted.
By requesting access, you agree to use this model only for non-commercial academic research. You acknowledge that this model is not offered to persons located in the European Union, and that access from the European Union is not granted.
Log in or Sign Up to review the conditions and access this model content.
GC-Cap-8B
GC-Cap-8B is an 8B vision-language model fine-tuned from Qwen3-VL-8B for game character captioning. It is part of the GC-Cap series (Game Character Captioning with Graph-based Evaluation).
Use restrictions
- Academic research only. Commercial use is not permitted under LICENSE.txt.
- Not offered in the European Union. This repository is gated, and
extra_gated_eu_disallowed: trueis set in the model card metadata. Hugging Face identifies the visitor by IP address and does not accept access requests from European Union IP addresses. This setting takes effect only because the repository is gated.
License
See LICENSE.txt.
Acknowledgements
This work is supported by the Tencent IEG Rhinoceros Bird Project.
- Downloads last month
- -