Downloads · 30 days
35
7% of all-time downloads
DeepSeek-R1-Distill-Qwen-7B-mlx-6Bit
ALYTV/DeepSeek-R1-Distill-Qwen-7B-mlx-6Bit
DeepSeek-R1-Distill-Qwen-7B-mlx-6Bit is a text generation model from ALYTV. 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 ALYTV/DeepSeek-R1-Distill-Qwen-7B-mlx-6Bit was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Qwen-7B using mlx-lm version 0.22.3.
All-time downloads
518
Public
Parameters
7.6B
6.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.2 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
ALYTV/DeepSeek-R1-Distill-Qwen-7B-mlx-6Bit
The Model ALYTV/DeepSeek-R1-Distill-Qwen-7B-mlx-6Bit was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Qwen-7B using mlx-lm version 0.22.3.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("ALYTV/DeepSeek-R1-Distill-Qwen-7B-mlx-6Bit")
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)
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- mit
- Created
- Jun 16, 2025
- Updated
- Jun 16, 2025