Downloads · 30 days
194
8% of all-time downloads
DeepSeek-R1-Distill-Llama-70B-Q4-mlx
strandline/DeepSeek-R1-Distill-Llama-70B-Q4-mlx
DeepSeek-R1-Distill-Llama-70B-Q4-mlx is a text generation model from strandline. 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 maus/DeepSeek-R1-Distill-Llama-70B-Q4-mlx was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Llama-70B using mlx-lm version 0.20.5.
All-time downloads
2.3K
Public
Parameters
70.6B
39.7 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors39.7 GB · 100%
Parameter types
How the weights are stored.
U3270.6B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
maus/DeepSeek-R1-Distill-Llama-70B-Q4-mlx
The Model maus/DeepSeek-R1-Distill-Llama-70B-Q4-mlx was converted to MLX format from deepseek-ai/DeepSeek-R1-Distill-Llama-70B using mlx-lm version 0.20.5.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("maus/DeepSeek-R1-Distill-Llama-70B-Q4-mlx")
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
- llama
- License
- mit
- Created
- Jan 31, 2025
- Updated
- Jan 31, 2025