Model Card for Mixtral-8x7B 4 bit

The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested.

For full details of this model please read our release blog post.

Instruction format

This format must be strictly respected, otherwise the model will generate sub-optimal outputs.

The template used to build a prompt for the Instruct model is defined as follows:

<s> [INST] Instruction [/INST] Model answer</s> [INST] Follow-up instruction [/INST]

Note that <s> and </s> are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings.

Run the model

# Install mlx, mlx-examples, huggingface-cli
pip install mlx
pip install huggingface_hub hf_transfer
git clone https://github.com/ml-explore/mlx-examples.git

# Download model
export HF_HUB_ENABLE_HF_TRANSFER=1
huggingface-cli download --local-dir Mixtral-8x7B-Instruct-v0.1-4-bit https://huggingface.co/hurongliang/Mixtral-8x7B-Instruct-v0.1-4-bit

# Run example
python mlx-examples/llms/mixtral/mixtral.py --model_path Mixtral-8x7B-Instruct-v0.1-4-bit