Commit History
-
Add RepoPeftBench corpus merge
El-Mouden Moncif +1: Claude Opus 5Joins Code2LoRA's benchmark (~500K assertion-completion items over 512 repos) to aligned6 (~27K prose QA over 2066 repos). The two are complementary: the benchmark showed the head learns a repo's stack and conventions but not what the project does, and exact-recall data is what addresses that. Carries RepoPeftBench's own by-repo partition through unchanged, and lets an eval assignment always win over a train one, so no repo can leak between train and cross-repo eval. Caps QA per repo (evo alone has ~1000/repo) so the exact recall task cannot swamp the prose QA. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>4f41179 -
Fix hypernetwork input collapse; add serving app + H100 deploy kit
El-Mouden Moncif +1: Claude Opus 5The trained head emitted a near-identical adapter for every repo (pairwise cosine 0.96) and scored worse than random noise on held-out repo text. Cause: ~64% of each 6-view embedding is a constant vector shared by all repos, which dominated the trunk (input cosine 0.73 -> 0.978 after the trunk). - MemoryLoRAHead: standardize the conditioning input via input_mean/input_std buffers fitted on train docs only and stored in the checkpoint, so training and inference apply the same transform. After 40 steps the emitted-adapter cosine dropped 0.96 -> 0.21. - Training: log the no-adapter baseline and delta_vs_baseline every eval, plus diag/adapter_cosine. Tracking only the adapted loss is why the collapse went unnoticed. - app/: Next.js app serving repo-personalized models over OpenAI- and Anthropic-compatible APIs for coding CLIs. - deploy/h100/: provisioning + training scripts for a single-GPU cloud run. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>f17edea