Qwen2.5-3B checkpoints for Defects4J unit-test generation with Online Policy Distillation and GRPO.
tomsawyer
tomhu
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Self-Evolving Coding Agents submitted a paper 1 day ago
Self-Evolving Coding Agents updated a model 2 days ago
tomhu/Qwen3-Coder-Next-SWE-Prune-41B-A3BOrganizations
None yet
models 47
tomhu/Qwen3-Coder-Next-SWE-Prune-41B-A3B
Text Generation • 41B • Updated • 185
tomhu/Qwen3-Coder-Next-SWE-Prune-26B-A3B
Text Generation • 26B • Updated • 81
tomhu/RL4TG-Qwen3-8B-Offline-SFT-GRPO
Text Generation • 8B • Updated • 17
tomhu/RL4TG-Qwen3-8B-OPD-GRPO
Text Generation • 8B • Updated • 18
tomhu/RL4TG-Qwen3-8B-Direct-GRPO
Text Generation • 8B • Updated • 20
tomhu/RL4TG-DeepSeek-Coder-1.3B-Coder6.7B-Offline-SFT-GRPO
Text Generation • 1B • Updated • 31
tomhu/RL4TG-DeepSeek-Coder-1.3B-GRPO
Text Generation • 1B • Updated • 37
tomhu/RL4TG-DeepSeek-Coder-1.3B-OPD6.7B-GRPO
Text Generation • 1B • Updated • 28
tomhu/RL4TG-DeepSeek-Coder-1.3B-OPD-33B-Teacher
Text Generation • 1B • Updated • 18
tomhu/RL4TG-DeepSeek-Coder-1.3B-OPD-6.7B-Teacher
Text Generation • 1B • Updated • 18