README.md

metadata

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

mlx-community/CodeLlama-7b-Python-4bit

This model was converted to MLX format from codellama/CodeLlama-7b-Python-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-Python-4bit")
response = generate(model, tokenizer, prompt="<s>[INST] <<SYS>> You are a helpful, respectful, and honest assistant. Always do... If you are unsure about an answer, truthfully say \"I don't know\" <</SYS>> What's the meaning of life [/INST]", verbose=True)