jb-01 / LoRA-TLE
Token-level adaptation of LoRA matrices for downstream task generalization.
☆14Updated 5 months ago
Related projects: ⓘ
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆34Updated 8 months ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆40Updated 8 months ago
- Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"☆22Updated 3 months ago
- Code for PHATGOOSE introduced in "Learning to Route Among Specialized Experts for Zero-Shot Generalization"☆76Updated 6 months ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆44Updated 8 months ago
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆46Updated 5 months ago
- ☆30Updated last month
- Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".☆81Updated 2 weeks ago
- ☆16Updated 3 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆56Updated 3 months ago
- Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"