madroid's picture
9b9571155e33d5a67e653f493580e9d259a040d9d88e56ffb7544518f753108b
37b5854 verified
|
raw
history blame
612 Bytes
metadata
license: apache-2.0
tags:
  - mlx

mlx-community/Mistral-7B-Instruct-v0.3-4bit

The Model mlx-community/Mistral-7B-Instruct-v0.3-4bit was converted to MLX format from mistralai/Mistral-7B-Instruct-v0.3 using mlx-lm version 0.14.3.

Use with mlx

pip install mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Mistral-7B-Instruct-v0.3-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)