GitHub · Python
Phoenix-chaser/CodeAgent-R
Auditable code-repair post-training platform: source-group-isolated QLoRA SFT, mutation-audited tasks, execution-based checkpoint selection, paired frozen-test evaluation. 3-seed protocol on Qwen2.5-Coder-7B: mean +1.7pp, zero regressions
- Stars
- 7
- Forks
- 0
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: benchmark, code-repair, evaluation, fine-tuning, llm, peft, qlora, reproducibility, sft
Latest data point: Nov 20, 2026 · 7 stars · 0 forks