Instructions to use usail-hkust/LLMLight-LightGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use usail-hkust/LLMLight-LightGPT with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="usail-hkust/LLMLight-LightGPT")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("usail-hkust/LLMLight-LightGPT")
model = AutoModelForCausalLM.from_pretrained("usail-hkust/LLMLight-LightGPT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use usail-hkust/LLMLight-LightGPT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "usail-hkust/LLMLight-LightGPT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "usail-hkust/LLMLight-LightGPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/usail-hkust/LLMLight-LightGPT

SGLang

How to use usail-hkust/LLMLight-LightGPT 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 "usail-hkust/LLMLight-LightGPT" \
    --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": "usail-hkust/LLMLight-LightGPT",
		"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 "usail-hkust/LLMLight-LightGPT" \
        --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": "usail-hkust/LLMLight-LightGPT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use usail-hkust/LLMLight-LightGPT with Docker Model Runner:
```
docker model run hf.co/usail-hkust/LLMLight-LightGPT
```

Haruto2099 commited on Feb 26, 2024

Commit

263c0c1

verified ·

1 Parent(s): e9a8b82

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -20,10 +20,10 @@ Please download the model and run the LLMLight framework by following the descri
 <a id="framework"></a>
-## 2 Framework:
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64207ca7e40f66bcd1e44959/HDBvVmYkTdShGfY5mnPGs.png)
 <a id="demo"></a>
-## 3 Demo:
 <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/64207ca7e40f66bcd1e44959/VhMOdEIjKeLml1WPcINqV.qt"></video>

 <a id="framework"></a>
+## 2 Framework
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64207ca7e40f66bcd1e44959/HDBvVmYkTdShGfY5mnPGs.png)
 <a id="demo"></a>
+## 3 Demo
 <video controls autoplay src="https://cdn-uploads.huggingface.co/production/uploads/64207ca7e40f66bcd1e44959/VhMOdEIjKeLml1WPcINqV.qt"></video>