arxiv:2409.10033
tomsawyer
tomhu
·
AI & ML interests
None yet
Organizations
None yet
models
16
tomhu/Qwen2.5-Coder-1.5B-SFT
2B
•
Updated
•
3
tomhu/Qwen2.5-Coder-1.5B-RL-ABLATION-TEST
2B
•
Updated
•
3
tomhu/Qwen2.5-Coder-1.5B-RL-ABLATION-CODE
2B
•
Updated
•
2
tomhu/Qwen2.5-Coder-1.5B-RL
2B
•
Updated
•
3
tomhu/Qwen3-4B-SFT
4B
•
Updated
•
6
tomhu/Qwen3-4B-RL-ABLATION-TEST-5000-step
2B
•
Updated
•
5
tomhu/Qwen3-4B-RL-ABLATION-CODE-5000-step
4B
•
Updated
•
5
tomhu/Qwen3-4B-RL-5000-step
4B
•
Updated
•
4
•
1
tomhu/Qwen2.5-Coder-3B-RL-Ablation-Test-5000-step
Updated
tomhu/Qwen2.5-Coder-3B-SFT
3B
•
Updated
•
3