Text Generation
Safetensors
llada
gptqmodel
FunAGI
int4
conversational
custom_code
4-bit precision
gptq
Instructions to use FunAGI/LLaDA-8B-Base-gptqmodel-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- vLLM
How to use FunAGI/LLaDA-8B-Base-gptqmodel-4bit with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "FunAGI/LLaDA-8B-Base-gptqmodel-4bit" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FunAGI/LLaDA-8B-Base-gptqmodel-4bit", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/FunAGI/LLaDA-8B-Base-gptqmodel-4bit
- SGLang
How to use FunAGI/LLaDA-8B-Base-gptqmodel-4bit 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 "FunAGI/LLaDA-8B-Base-gptqmodel-4bit" \ --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": "FunAGI/LLaDA-8B-Base-gptqmodel-4bit", "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 "FunAGI/LLaDA-8B-Base-gptqmodel-4bit" \ --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": "FunAGI/LLaDA-8B-Base-gptqmodel-4bit", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use FunAGI/LLaDA-8B-Base-gptqmodel-4bit with Docker Model Runner:
docker model run hf.co/FunAGI/LLaDA-8B-Base-gptqmodel-4bit
Download quantize_config.json from FunAGI/LLaDA-8B-Base-gptqmodel-4bit: direct link, hf CLI and curl.
- Browser
- Download file 432 Bytes
-
https://huggingface.co/FunAGI/LLaDA-8B-Base-gptqmodel-4bit/resolve/main/quantize_config.json
- Command line
-
hf download hf://FunAGI/LLaDA-8B-Base-gptqmodel-4bit/quantize_config.json
-
curl -L -o quantize_config.json https://huggingface.co/FunAGI/LLaDA-8B-Base-gptqmodel-4bit/resolve/main/quantize_config.json
432 Bytes
| { | |
| "bits": 4, | |
| "group_size": 128, | |
| "desc_act": true, | |
| "sym": false, | |
| "lm_head": false, | |
| "quant_method": "gptq", | |
| "checkpoint_format": "gptq", | |
| "pack_dtype": "int32", | |
| "meta": { | |
| "quantizer": [ | |
| "gptqmodel:2.0.0-dev" | |
| ], | |
| "uri": "https://github.com/modelcloud/gptqmodel", | |
| "damp_percent": 0.01, | |
| "damp_auto_increment": 0.0025, | |
| "static_groups": false, | |
| "true_sequential": true, | |
| "mse": 0.0 | |
| } | |
| } |