Sponsored by
APIMart
ganglii / DRPO-7B
Model's Last Updated: March 30 2026
Introduction of DRPO-7B
Model Details of DRPO-7B
DRPO-7B
This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-7B on the agentica-org/DeepScaleR-Preview-Dataset .
It was fine-tuned as part of the paper Efficient Reasoning via Decoupled Reward Policy Optimization ( paper link ).
The code is available at: https://github.com/Optimization-AI/DRPO
Below are comparisons with baseline models and baseline methods. Left is for fine-tuning 1.5B model and right is for fine-tuning 7B model. Grey lines represent the base model performance before finetuning, with generation length of 4698 for 1.5B model and 4119 for 7B model. Squares denote models trained with reference methods without length penalties (i.e., $\lambda$=+$\infty$ for DRPO, $\alpha=0$ for RLOO-LP, $\beta=0$ for ALP, $w=0$ for HAPO). Triangles denote the models trained by other works.
Runs of ganglii DRPO-7B on huggingface.co
35
Total runs
0
24-hour runs
-2
3-day runs
-13
7-day runs
-265
30-day runs
More Information About DRPO-7B huggingface.co Model
Url of DRPO-7B
DRPO-7B huggingface.co Url
Provider of DRPO-7B huggingface.co
Other API from ganglii
Total runs:
10
Run Growth:
-35
Growth Rate:
-350.00%
Total runs:
10
Run Growth:
-1
Growth Rate:
-10.00%
Total runs:
1
Run Growth:
-114
Growth Rate:
-11400.00%