Text Generation
Safetensors
English
Chinese
vllm
llama
nanbeige
int4
w4a16
gptq
auto-round
marlin
rtx-3090
conversational
4-bit precision
Instructions to use Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- vLLM
How to use Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound
- SGLang
How to use Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound 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 "Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound" \ --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": "Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound", "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 "Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound" \ --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": "Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound with Docker Model Runner:
docker model run hf.co/Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound
Download quantization_config.json from Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound: direct link, hf CLI and curl.
- Browser
- Download file 269 Bytes
-
https://huggingface.co/Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound/resolve/main/quantization_config.json
- Command line
-
hf download hf://Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound/quantization_config.json
-
curl -L -o quantization_config.json https://huggingface.co/Tech2wild/Nanbeige4.3-33B-W4A16-AutoRound/resolve/main/quantization_config.json
269 Bytes
| { | |
| "bits": 4, | |
| "data_type": "int", | |
| "group_size": 128, | |
| "sym": true, | |
| "iters": 100, | |
| "autoround_version": "0.16.1", | |
| "lm_head": false, | |
| "provider": "auto-round", | |
| "quant_method": "gptq", | |
| "desc_act": false, | |
| "true_sequential": false, | |
| "damp_percent": 0.01 | |
| } |