Downloads · 30 days
15
8% of all-time downloads
DeepScaleR-1.5B-Preview-Q4-mlx
motionlabs/DeepScaleR-1.5B-Preview-Q4-mlx
DeepScaleR-1.5B-Preview-Q4-mlx is a text generation model from motionlabs. 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 reflex-ai/DeepScaleR-1.5B-Preview-Q4-mlx was converted to MLX format from agentica-org/DeepScaleR-1.5B-Preview using mlx-lm version 0.20.5.
All-time downloads
182
Public
Parameters
1.8B
1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1000 MB · 99%
Parameter types
How the weights are stored.
U321.8B · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
saneowl/DeepScaleR-1.5B-Preview-Q4-mlx
The Model reflex-ai/DeepScaleR-1.5B-Preview-Q4-mlx was converted to MLX format from agentica-org/DeepScaleR-1.5B-Preview using mlx-lm version 0.20.5.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("saneowl/DeepScaleR-1.5B-Preview-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
- qwen2
- License
- mit
- Languages
- en
- Created
- Feb 20, 2025
- Updated
- Feb 20, 2025