README.md

metadata

datasets:
  - gsarti/clean_mc4_it
language:
  - it
library_name: transformers
tags:
  - mlx

RiTA-nlp/llama3-tweety-8b-italian-mlx-4bit

The Model RiTA-nlp/llama3-tweety-8b-italian-mlx-4bit was converted to MLX format from RiTA-nlp/llama3-tweety-8b-italian using mlx-lm version 0.15.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("RiTA-nlp/llama3-tweety-8b-italian-mlx-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)