README.md

metadata

language:
  - code
license: llama2
tags:
  - llama-2
  - mlx
pipeline_tag: text-generation

https://media.discordapp.net/attachments/989904887330521099/1201717650128896070/Llama_Coding_on_MacBook_1.png?ex=65cad5c6&is=65b860c6&hm=8008a5817272fa49fca67143516563b2578accf263cc04d6768e689c1be2f483&=&format=webp&quality=lossless&width=1372&height=1372

mlx-community/CodeLlama-7b-Instruct-hf-4bit-MLX

This model was converted to MLX format from codellama/CodeLlama-7b-Instruct-hf. 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/CodeLlama-7b-Instruct-hf-4bit-MLX")
response = generate(model, tokenizer, prompt="hello", verbose=True)