Downloads · 30 days
29
3% of all-time downloads
kaxap/mlx-DeepSeek-R1-0528-2bit
mlx-DeepSeek-R1-0528-2bit is a text generation model from kaxap. Use it when you need the model to write or continue text. It is set up for mlx. The card lists the license as mit.
This model kaxap/mlx-DeepSeek-R1-0528-2bit was converted to MLX format from deepseek-ai/DeepSeek-R1-0528 using mlx-lm version 0.25.2.
Downloads · 30 days
29
3% of all-time downloads
All-time downloads
844
Public
Parameters
671B
210 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors210 GB · 100%
How the weights are stored.
U32671B · 100%
From the Hugging Face model README
This model kaxap/mlx-DeepSeek-R1-0528-2bit was converted to MLX format from deepseek-ai/DeepSeek-R1-0528 using mlx-lm version 0.25.2.
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("kaxap/mlx-DeepSeek-R1-0528-2bit")
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)