A RL-tuned version of R1-Qwen2.5 1.5B, which improves the math performance compared to the original, distilled model significantly. One of their main findings is that the incorrect responses were three times longer than the correct ones.
Specs
Params1.5B
LicenseMIT
Tags
modelsmodels/llmsmodels/llms/reasoningartifacts/7
RAM score
—
Hugging Face Downloads
3.9K
last 30d
730.8K
all time
HF Likes
584
Relative Adoption Metric contextualizes downloads against the model's size bucket.
VAIL Fingerprint
0076:00b0:00f2:0120:0225:036c:0654:4758
Explore other models with behavioral similarity to DeepScaleR-1.5B-Preview.
Related Models
