MLX
Safetensors
mixtral
kd7's picture
Upload folder using huggingface_hub
f4ed3a3 verified
|
raw
history blame
737 Bytes
metadata
language:
  - fr
  - it
  - de
  - es
  - en
license: apache-2.0
tags:
  - mlx
inference:
  parameters:
    temperature: 0.5
widget:
  - messages:
      - role: user
        content: What is your favorite condiment?

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

This model was converted to MLX format from mistralai/Mixtral-8x7B-Instruct-v0.1 using mlx-lm version 0.12.0. 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-Instruct-v0.1-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)