nmaher/repro-transformers-with-rl-or-sft-provably-learn-sparse-boolean-functions-but-differently
0
Update logbook: Reproduction: Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But Differently
Update logbook: Reproduction: Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But Differently
initial commit
