README.md

metadata

license: apache-2.0
datasets:
  - CohereForAI/aya_dataset
  - argilla/databricks-dolly-15k-curated-multilingual
  - Gael540/dataSet_ens_sup_fr-v1
  - ai2-adapt-dev/flan_v2_converted
  - OpenAssistant/oasst1
language:
  - fr
  - en
  - de
  - it
  - es
base_model: OpenLLM-France/Lucie-7B-Instruct-human-data
pipeline_tag: text-generation
tags:
  - mlx

alexgusevski/Lucie-7B-Instruct-human-data-q8-mlx

The Model alexgusevski/Lucie-7B-Instruct-human-data-q8-mlx was converted to MLX format from OpenLLM-France/Lucie-7B-Instruct-human-data using mlx-lm version 0.21.4.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("alexgusevski/Lucie-7B-Instruct-human-data-q8-mlx")

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)