README.md

metadata

pipeline_tag: text-generation
inference: true
license: apache-2.0
datasets:
  - simplescaling/s1K
tags:
  - mlx
base_model: simplescaling/s1-32B

moot20/s1-32B-MLX-6bits

The Model moot20/s1-32B-MLX-6bits was converted to MLX format from simplescaling/s1-32B using mlx-lm version 0.21.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("moot20/s1-32B-MLX-6bits")

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)