README.md

metadata

license: apache-2.0
tags:
  - finetuned
  - mlx
pipeline_tag: text-generation
inference: true
widget:
  - messages:
      - role: user
        content: What is your favorite condiment?

lucataco/Mistral-7B-Instruct-v0.1-4bit

This model was converted to MLX format from mistralai/Mistral-7B-Instruct-v0.1 using mlx-lm version 0.10.0. 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("lucataco/Mistral-7B-Instruct-v0.1-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)