MLX
mixtral
Mixture of Experts
mzbac's picture
Upload folder using huggingface_hub
5e7d4bd verified
|
raw
history blame
556 Bytes
metadata
language:
  - fr
  - it
  - de
  - es
  - en
license: apache-2.0
tags:
  - mlx

mlx-community/Mixtral-8x7B-v0.1-hf-4bit-mlx

This model was converted to MLX format from mistralai/Mixtral-8x7B-v0.1. Refer to the original model card for more details on the model.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Mixtral-8x7B-v0.1-hf-4bit-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)