README.md

metadata

base_model: mlx-community/Qwen2.5-0.5B-Instruct-4bit
language:
  - en
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct/blob/main/LICENSE
pipeline_tag: text-generation
tags:
  - chat
  - mlx
  - mlx

jilid_qwen2.5_0.5B_4bit

The Model jilid_qwen2.5_0.5B_4bit was converted to MLX format from mlx-community/Qwen2.5-0.5B-Instruct-4bit using mlx-lm version 0.21.5.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("jilid_qwen2.5_0.5B_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)