metadata
base_model: sm54/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B
library_name: transformers
tags:
- mergekit
- merge
- mlx
- mlx-my-repo
bobig/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-mlx-3Bit
The Model bobig/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-mlx-3Bit was converted to MLX format from sm54/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B using mlx-lm version 0.21.5.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("bobig/FuseO1-DeepSeekR1-QwQ-SkyT1-Flash-32B-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)