Instructions to use mrdmnd/llada-8b-instruct-4bit-gptq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Local Apps Settings
- vLLM
How to use mrdmnd/llada-8b-instruct-4bit-gptq with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mrdmnd/llada-8b-instruct-4bit-gptq" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mrdmnd/llada-8b-instruct-4bit-gptq", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/mrdmnd/llada-8b-instruct-4bit-gptq
- SGLang
How to use mrdmnd/llada-8b-instruct-4bit-gptq 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 "mrdmnd/llada-8b-instruct-4bit-gptq" \ --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": "mrdmnd/llada-8b-instruct-4bit-gptq", "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 "mrdmnd/llada-8b-instruct-4bit-gptq" \ --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": "mrdmnd/llada-8b-instruct-4bit-gptq", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use mrdmnd/llada-8b-instruct-4bit-gptq with Docker Model Runner:
docker model run hf.co/mrdmnd/llada-8b-instruct-4bit-gptq
Update README.md
Browse files
README.md
CHANGED
|
@@ -156,4 +156,6 @@ def quantize_model() -> None:
|
|
| 156 |
@app.local_entrypoint()
|
| 157 |
def main():
|
| 158 |
quantize_model.remote()
|
| 159 |
-
```
|
|
|
|
|
|
|
|
|
| 156 |
@app.local_entrypoint()
|
| 157 |
def main():
|
| 158 |
quantize_model.remote()
|
| 159 |
+
```
|
| 160 |
+
|
| 161 |
+
I think I also had to manually change something in the config.json -- needed to be "block_name_to_quantize": "model.transformer.blocks" instead of whatever it was, maybe "model_block_name_to_quantize" as the key or something.
|