SpectralPO
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Organization Card
This repo contains all the models for paper -
Spectral Policy Optimization: Coloring your Incorrect Reasoning in GRPO
-PLC
Collections
6
models
21
SpectralPO/DeepSeek-R1-Distill-Llama-8B-SPO
Updated
•
24
SpectralPO/DeepSeek-R1-Distill-Llama-8B-GRPO
Updated
•
9
SpectralPO/Qwen2.5-32B-Instruct-GRPO
Updated
•
7
SpectralPO/Qwen2.5-32B-Instruct-SPO
Updated
•
8
SpectralPO/32B-SPO-GRPO-mixed
Updated
•
5
SpectralPO/DeepSeek-R1-Distill-Qwen-14B-GRPO
Updated
•
9
SpectralPO/DeepSeek-R1-Distill-Qwen-SPO
Updated
•
27
SpectralPO/Qwen2.5-14B-Instruct-SPO
Updated
•
7
SpectralPO/Qwen2.5-14B-Instruct-GRPO
Updated
•
8
SpectralPO/extraSPO
Updated
•
5
datasets
0
None public yet