ssmmzz/DeepSeek-R1-Distill-Qwen-1.5B-GRPO
Updated
Alex Su
ssmmzz
AI & ML interests
None yet
Recent Activity
upvoted
a
collection
about 1 month ago
Pixel-Reasoner
upvoted
a
paper
about 2 months ago
Pixel Reasoner: Incentivizing Pixel-Space Reasoning with
Curiosity-Driven Reinforcement Learning
Organizations
None yet
models
10
ssmmzz/axolotl-lora-checkpoint-181-correctness-only-merged
Updated
ssmmzz/axolotl-lora-checkpoint-724-correctness-only
Updated
ssmmzz/axolotl-lora-checkpoint-543-correctness-only
Updated
ssmmzz/axolotl-lora-checkpoint-362-correctness-only
Updated
ssmmzz/axolotl-lora-checkpoint-181-correctness-only
Updated
ssmmzz/axolotl-lora-2000-complete
Updated
ssmmzz/axolotl-lora-1500-complete
Updated
ssmmzz/axolotl-lora-1000-complete
Updated
ssmmzz/axolotl-lora-500-complete
Updated
datasets
51
ssmmzz/carla25k
Updated
•
2
ssmmzz/fuckyou
Viewer
•
Updated
•
256
•
23
ssmmzz/label_Sim
Viewer
•
Updated
•
279
•
25
ssmmzz/label_Coh
Viewer
•
Updated
•
391
•
29
ssmmzz/label_Suc
Viewer
•
Updated
•
511
•
27
ssmmzz/label_Cor
Viewer
•
Updated
•
640
•
26
ssmmzz/label
Viewer
•
Updated
•
18.2k
•
42
ssmmzz/mixed_helsteer_combined_format
Viewer
•
Updated
•
18.7k
•
20
ssmmzz/label-only-correctness
Viewer
•
Updated
•
6.55k
•
22
ssmmzz/error_samples_only_test
Viewer
•
Updated
•
1.74k
•
28