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

Libraries

How to use hfl/chinese-mixtral-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="hfl/chinese-mixtral-gguf",
	filename="ggml-model-iq1_s.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use hfl/chinese-mixtral-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf hfl/chinese-mixtral-gguf:IQ1_S
# Run inference directly in the terminal:
llama-cli -hf hfl/chinese-mixtral-gguf:IQ1_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf hfl/chinese-mixtral-gguf:IQ1_S
# Run inference directly in the terminal:
llama-cli -hf hfl/chinese-mixtral-gguf:IQ1_S

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf hfl/chinese-mixtral-gguf:IQ1_S
# Run inference directly in the terminal:
./llama-cli -hf hfl/chinese-mixtral-gguf:IQ1_S

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf hfl/chinese-mixtral-gguf:IQ1_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hfl/chinese-mixtral-gguf:IQ1_S

Use Docker

docker model run hf.co/hfl/chinese-mixtral-gguf:IQ1_S

LM Studio
Jan
Ollama
How to use hfl/chinese-mixtral-gguf with Ollama:
```
ollama run hf.co/hfl/chinese-mixtral-gguf:IQ1_S
```

Unsloth Studio new

How to use hfl/chinese-mixtral-gguf with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for hfl/chinese-mixtral-gguf to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for hfl/chinese-mixtral-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hfl/chinese-mixtral-gguf to start chatting

Docker Model Runner
How to use hfl/chinese-mixtral-gguf with Docker Model Runner:
```
docker model run hf.co/hfl/chinese-mixtral-gguf:IQ1_S
```

Lemonade

How to use hfl/chinese-mixtral-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hfl/chinese-mixtral-gguf:IQ1_S

Run and chat with the model

lemonade run user.chinese-mixtral-gguf-IQ1_S

List all available models

lemonade list

Chinese-Mixtral-GGUF

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

This repository contains the GGUF-v3 models (llama.cpp compatible) for Chinese-Mixtral (this is not a chat/instruction model).

Performance

Metric: PPL, lower is better

Quant	PPL
IQ1_S	20.7314 +/- 0.22627
IQ2_XXS	8.5981 +/- 0.09267
IQ2_XS	6.9784 +/- 0.07476
Q2_K	5.1846 +/- 0.05533
IQ3_XXS	4.5990 +/- 0.04969
Q3_K	4.5545 +/- 0.04893
Q4_0	4.4917 +/- 0.04844
Q4_K	4.4488 +/- 0.04813
Q5_0	4.4224 +/- 0.04753
Q5_K	4.4192 +/- 0.04768
Q6_K	4.4092 +/- 0.04758
Q8_0	4.4076 +/- 0.04746
F16	x

Due to the file size limitation, for F16 model, please use cat command to concatenate all parts into a single file. You must concatenate these parts in order.

Others

For Hugging Face version, please see: https://huggingface.co/hfl/chinese-mixtral
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}
}

Downloads last month: 212

GGUF

Model size

47B params

Architecture

llama

Hardware compatibility

1-bit

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including hfl/chinese-mixtral-gguf

Chinese Mixtral series

Collection

This collection hosts the Chinese-Mixtral LLMs, including Full weight, LoRA, and GGUF formats. • 6 items • Updated May 7, 2024 • 1

Paper for hfl/chinese-mixtral-gguf

Rethinking LLM Language Adaptation: A Case Study on Chinese Mixtral

Paper • 2403.01851 • Published Mar 4, 2024