Instructions to use tencent/Tencent-Hunyuan-Large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use tencent/Tencent-Hunyuan-Large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="tencent/Tencent-Hunyuan-Large")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("tencent/Tencent-Hunyuan-Large", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use tencent/Tencent-Hunyuan-Large with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "tencent/Tencent-Hunyuan-Large" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tencent/Tencent-Hunyuan-Large", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/tencent/Tencent-Hunyuan-Large
- SGLang
How to use tencent/Tencent-Hunyuan-Large 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 "tencent/Tencent-Hunyuan-Large" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tencent/Tencent-Hunyuan-Large", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "tencent/Tencent-Hunyuan-Large" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "tencent/Tencent-Hunyuan-Large", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use tencent/Tencent-Hunyuan-Large with Docker Model Runner:
docker model run hf.co/tencent/Tencent-Hunyuan-Large
Add llama.cpp support
Dear Tencent AI Team,
I hope this message finds you well. I would like to start by congratulating you on the impressive release of the Hunyuan language model. Its capabilities are truly remarkable, and I'm excited to see more advancements coming from Tencent.
I am writing to kindly request that you consider adding support for Hunyuan in llama.cpp. Llama.cpp has become one of the most widely used tools by independent researchers, developers, and AI enthusiasts due to its lightweight design and ability to run efficiently on consumer-grade hardware. Many hobbyists and smaller-scale developers rely on llama.cpp for experimenting with large language models without the need for expensive infrastructure.
Supporting llama.cpp would significantly extend Hunyuan's accessibility and adoption, especially among amateur developers and communities who may not have access to large-scale cloud resources. It would also foster a broader ecosystem of innovation around your model, as more people will be able to experiment and build upon Hunyuan’s capabilities.
I believe that adding llama.cpp support will greatly enhance Hunyuan's reach and impact in the AI community, encouraging a wider range of applications and contributions.
Thank you for considering this suggestion, and I look forward to seeing the continued success of Hunyuan.
Warm regards,
Charles McSneed
We need to ask for support from llama.cpp team.