metadata

license: apache-2.0
datasets:
  - yahma/alpaca-cleaned
  - cmh/alpaca_data_cleaned_fr_52k
  - Magpie-Align/Magpie-Gemma2-Pro-200K-Filtered
  - allenai/WildChat-1M
language:
  - fr
  - en
base_model: OpenLLM-France/Lucie-7B-Instruct
pipeline_tag: text-generation
tags:
  - mlx

mlx-community/Lucie-7B-Instruct-4bit

The Model mlx-community/Lucie-7B-Instruct-4bit was converted to MLX format from OpenLLM-France/Lucie-7B-Instruct using mlx-lm version 0.21.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Lucie-7B-Instruct-4bit")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)