README.md

metadata

license: other
license_name: qwen-research
license_link: https://huggingface.co./Qwen/Qwen2.5-3B/blob/main/LICENSE
language:
  - en
pipeline_tag: text-generation
base_model: Qwen/Qwen2.5-3B
tags:
  - mlx

ivanfioravanti/Qwen2.5-3B-italian-wine-fp16

The Model ivanfioravanti/Qwen2.5-3B-italian-wine-fp16 was converted to MLX format from Qwen/Qwen2.5-3B using mlx-lm version 0.20.6.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("ivanfioravanti/Qwen2.5-3B-italian-wine-fp16")

prompt="hello"

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

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