RL4TG

tomhu 's Collections

RL4TG

Personalized-Emotional-Support

updated 10 days ago

Qwen2.5-3B checkpoints for Defects4J unit-test generation with Online Policy Distillation and GRPO.

Upvote

tomhu/RL4TG-Qwen2.5-3B-OPD-7B-Teacher

Text Generation • 3B • Updated 15 days ago • 988

Note Online Policy Distillation (OPD); final step 152
tomhu/RL4TG-Qwen2.5-3B-OPD-14B-Teacher

Text Generation • 3B • Updated 19 days ago • 232

Note Online Policy Distillation (OPD); final step 152
tomhu/RL4TG-Qwen2.5-3B-GRPO

Text Generation • 3B • Updated 19 days ago • 595

Note GRPO; step 98 (2 epochs)
tomhu/RL4TG-Qwen2.5-3B-OPD-GRPO

Text Generation • 3B • Updated 19 days ago • 616

Note OPD followed by GRPO; step 98 (2 epochs)
tomhu/RL4TG-Qwen2.5-3B-Coder7B-Offline-SFT

Text Generation • 3B • Updated 17 days ago • 25
tomhu/RL4TG-Qwen2.5-3B-Official-D4J-SFT

Text Generation • 3B • Updated 17 days ago • 31
tomhu/RL4TG-Qwen2.5-3B-Coder7B-Offline-SFT-GRPO

Text Generation • 3B • Updated 16 days ago • 169
tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT

Text Generation • 0.7B • Updated 13 days ago • 30
tomhu/RL4TG-DeepSeek-Coder-1.3B-Official-D4J-SFT

Text Generation • 1B • Updated 13 days ago • 17
tomhu/RL4TG-DeepSeek-Coder-1.3B-OPD-6.7B-Teacher

Text Generation • 1B • Updated 13 days ago • 17
tomhu/RL4TG-DeepSeek-Coder-1.3B-OPD-33B-Teacher

Text Generation • 1B • Updated 13 days ago • 17
tomhu/RL4TG-DeepSeek-Coder-1.3B-OPD6.7B-GRPO

Text Generation • 1B • Updated 13 days ago • 28
tomhu/RL4TG-DeepSeek-Coder-1.3B-GRPO

Text Generation • 1B • Updated 13 days ago • 36
tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO

Text Generation • 1B • Updated 13 days ago • 30
tomhu/RL4TG-Qwen3-8B-OPD-GRPO

Text Generation • 8B • Updated 10 days ago • 16
tomhu/RL4TG-Qwen3-8B-Offline-SFT-GRPO

Text Generation • 8B • Updated 10 days ago • 16
tomhu/RL4TG-Qwen3-8B-Direct-GRPO

Text Generation • 8B • Updated 10 days ago • 19

Upvote