metadata
base_model: unsloth/DeepSeek-R1-Distill-Qwen-32B
language:
- en
license: apache-2.0
library_name: transformers
tags:
- deepseek
- qwen
- qwen2
- unsloth
- transformers
- mlx
- mlx-my-repo
McG-221/DeepSeek-R1-Distill-Qwen-32B-mlx-8Bit
The Model McG-221/DeepSeek-R1-Distill-Qwen-32B-mlx-8Bit was converted to MLX format from unsloth/DeepSeek-R1-Distill-Qwen-32B using mlx-lm version 0.26.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("McG-221/DeepSeek-R1-Distill-Qwen-32B-mlx-8Bit")
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)