Downloads · 30 days
35
9% of all-time downloads
DeepSeek-R1-Distill-Qwen-7B-MLX-4bit
moot20/DeepSeek-R1-Distill-Qwen-7B-MLX-4bit
DeepSeek-R1-Distill-Qwen-7B-MLX-4bit is a text generation model from moot20. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
The Model moot20/DeepSeek-R1-Distill-Qwen-7B-MLX-4bit was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Qwen-7B using mlx-lm version 0.21.1.
All-time downloads
389
Public
Parameters
7.6B
4.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors4.3 GB · 100%
Parameter types
How the weights are stored.
U327.6B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
moot20/DeepSeek-R1-Distill-Qwen-7B-MLX-4bit
The Model moot20/DeepSeek-R1-Distill-Qwen-7B-MLX-4bit was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Qwen-7B using mlx-lm version 0.21.1.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("moot20/DeepSeek-R1-Distill-Qwen-7B-MLX-4bit")
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)
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- mit
- Created
- Jan 28, 2025
- Updated
- Jan 28, 2025