README.md

metadata

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

flohannes/mistral-7b-instruct-4bit-1k

The Model flohannes/mistral-7b-instruct-4bit-1k was converted to MLX format from mlx-community/Mistral-7B-Instruct-v0.2-4bit using mlx-lm version 0.17.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("flohannes/mistral-7b-instruct-4bit-1k")
response = generate(model, tokenizer, prompt="hello", verbose=True)