Modelpublic

qurk41/rStar2-Agent-14B-mlx-4Bit

sourceHugging Facemitupdated 1y agoView on Hugging Face

0likes32downloads

Model Card

qurk41/rStar2-Agent-14B-mlx-4Bit

The Model qurk41/rStar2-Agent-14B-mlx-4Bit was converted to MLX format from rstar2-reproduce/rStar2-Agent-14B using mlx-lm version 0.26.4.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("qurk41/rStar2-Agent-14B-mlx-4Bit")

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)