Instructions to use openlmlab/open-chinese-llama-7b-patch with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openlmlab/open-chinese-llama-7b-patch with Transformers:

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

pipe = pipeline("text-generation", model="openlmlab/open-chinese-llama-7b-patch")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openlmlab/open-chinese-llama-7b-patch")
model = AutoModelForCausalLM.from_pretrained("openlmlab/open-chinese-llama-7b-patch")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openlmlab/open-chinese-llama-7b-patch with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openlmlab/open-chinese-llama-7b-patch"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openlmlab/open-chinese-llama-7b-patch",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openlmlab/open-chinese-llama-7b-patch

SGLang

How to use openlmlab/open-chinese-llama-7b-patch 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 "openlmlab/open-chinese-llama-7b-patch" \
    --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": "openlmlab/open-chinese-llama-7b-patch",
		"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 "openlmlab/open-chinese-llama-7b-patch" \
        --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": "openlmlab/open-chinese-llama-7b-patch",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openlmlab/open-chinese-llama-7b-patch with Docker Model Runner:
```
docker model run hf.co/openlmlab/open-chinese-llama-7b-patch
```

open-chinese-llama-7b-patch

Commit History

Update generation_config.json

d7e5643

Shuo Zhang commited on Apr 27, 2023

Update generation_config.json

f663bd0

Shuo Zhang commited on Apr 27, 2023

Update config.json

c5675d6

Shuo Zhang commited on Apr 25, 2023

Update README.md

47bdbd4

Shuo Zhang commited on Apr 25, 2023

Update README.md

1ba8c12

Shuo Zhang commited on Apr 25, 2023

Update README.md

72be2ab

Shuo Zhang commited on Apr 25, 2023

Upload 3 files

c3e3195

Shuo Zhang commited on Apr 25, 2023