README.md

metadata

base_model: >-
  TheBlueObserver/Llama-3.2-3B-Instruct-Unsloth-healthcare-recurv-recurv-huatuo-16bit-1epoch-merged
library_name: transformers
tags:
  - mlx

TheBlueObserver/Llama-3.2-3B-Instruct-Unsloth-healthcare-recurv-recurv-huatuo-16bit-1epoch-merged-MLX-196c8

The Model TheBlueObserver/Llama-3.2-3B-Instruct-Unsloth-healthcare-recurv-recurv-huatuo-16bit-1epoch-merged-MLX-196c8 was converted to MLX format from TheBlueObserver/Llama-3.2-3B-Instruct-Unsloth-healthcare-recurv-recurv-huatuo-16bit-1epoch-merged using mlx-lm version 0.20.2.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("TheBlueObserver/Llama-3.2-3B-Instruct-Unsloth-healthcare-recurv-recurv-huatuo-16bit-1epoch-merged-MLX-196c8")

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)