Text Generation
Safetensors
vllm
hy_v3
gptq
4-bit precision
quantization
hunyuan
hy3
Mixture of Experts
rtn
conversational
Instructions to use avtc/Hy3-GPTQ-RTN-4bit-tp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- vLLM
How to use avtc/Hy3-GPTQ-RTN-4bit-tp8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "avtc/Hy3-GPTQ-RTN-4bit-tp8" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "avtc/Hy3-GPTQ-RTN-4bit-tp8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/avtc/Hy3-GPTQ-RTN-4bit-tp8
- SGLang
How to use avtc/Hy3-GPTQ-RTN-4bit-tp8 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 "avtc/Hy3-GPTQ-RTN-4bit-tp8" \ --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": "avtc/Hy3-GPTQ-RTN-4bit-tp8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "avtc/Hy3-GPTQ-RTN-4bit-tp8" \ --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": "avtc/Hy3-GPTQ-RTN-4bit-tp8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use avtc/Hy3-GPTQ-RTN-4bit-tp8 with Docker Model Runner:
docker model run hf.co/avtc/Hy3-GPTQ-RTN-4bit-tp8
- Xet hash:
- 1f93bb655241e29f825d0dd47279e233afe6d6d514e1951879c1eb0a69930f2f
- Size of remote file:
- 4.29 GB
- SHA256:
- 7298b1f4c48b9b5bfebadbdbe42f23226dd73cfc2acfb1f5a0a9c3442d906812
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.