Instructions to use hfl/chinese-mixtral-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hfl/chinese-mixtral-instruct with Transformers:

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

pipe = pipeline("text-generation", model="hfl/chinese-mixtral-instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hfl/chinese-mixtral-instruct")
model = AutoModelForCausalLM.from_pretrained("hfl/chinese-mixtral-instruct")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hfl/chinese-mixtral-instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hfl/chinese-mixtral-instruct

SGLang

How to use hfl/chinese-mixtral-instruct 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 "hfl/chinese-mixtral-instruct" \
    --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": "hfl/chinese-mixtral-instruct",
		"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 "hfl/chinese-mixtral-instruct" \
        --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": "hfl/chinese-mixtral-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hfl/chinese-mixtral-instruct with Docker Model Runner:
```
docker model run hf.co/hfl/chinese-mixtral-instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Chinese-Mixtral-Instruct

Chinese Mixtral GitHub repository: https://github.com/ymcui/Chinese-Mixtral

This repository contains Chinese-Mixtral-Instruct, which is further tuned with instruction data on Chinese-Mixtral, where Chinese-Mixtral is build on top of Mixtral-8x7B-v0.1.

Note: this is an instruction (chat) model, which can be used for conversation, QA, etc.

Others

For LoRA-only model, please see: https://huggingface.co/hfl/chinese-mixtral-instruct-lora
For GGUF model (llama.cpp compatible), please see: https://huggingface.co/hfl/chinese-mixtral-instruct-gguf
If you have questions/issues regarding this model, please submit an issue through https://github.com/ymcui/Chinese-Mixtral/.

Citation

Please consider cite our paper if you use the resource of this repository. Paper link: https://arxiv.org/abs/2403.01851

@article{chinese-mixtral,
      title={Rethinking LLM Language Adaptation: A Case Study on Chinese Mixtral}, 
      author={Cui, Yiming and Yao, Xin},
      journal={arXiv preprint arXiv:2403.01851},
      url={https://arxiv.org/abs/2403.01851},
      year={2024}
}