metadata
license: mit
thumbnail: >-
https://cdn-uploads.huggingface.co/production/uploads/6625f4a8a8d1362ebcc3851a/9TIfNBdy29CDnn8NNIQPt.jpeg
language:
- en
base_model: ArliAI/R1-8B-ArliAI-RpR-v2
tags:
- mlx
fengpeisheng1/R1-8B-ArliAI-RpR-v2-mlx-3Bit
The Model fengpeisheng1/R1-8B-ArliAI-RpR-v2-mlx-3Bit was converted to MLX format from ArliAI/R1-8B-ArliAI-RpR-v2 using mlx-lm version 0.22.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("fengpeisheng1/R1-8B-ArliAI-RpR-v2-mlx-3Bit")
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)