kmeng01 / rome
Locating and editing factual associations in GPT (NeurIPS 2022)
☆620Updated 11 months ago
Alternatives and similar repositories for rome:
Users that are interested in rome are comparing it to the libraries listed below
- Mass-editing thousands of facts into a transformer memory (ICLR 2023)☆477Updated last year
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆517Updated 2 months ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆816Updated 8 months ago
- Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"☆478Updated 3 months ago
- RewardBench: the first evaluation tool for reward models.☆553Updated last month
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆431Updated 5 months ago
- This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large Language Models.☆458Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆485Updated 10 months ago
- OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.☆555Updated last year
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆830Updated this week
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆626Updated 8 months ago
- Must-read Papers on Knowledge Editing for Large Language Models.☆1,054Updated last month
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆766Updated last year
- ☆201Updated last year
- A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic…☆338Updated this week
- Codebase for Merging Language Models (ICML 2024)☆812Updated 11 months ago
- Using sparse coding to find distributed representations used by neural networks.☆230Updated last year
- ☆450Updated 8 months ago
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆805Updated 9 months ago
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆544Updated last year
- ☆217Updated 6 months ago
- Code and data for "Lost in the Middle: How Language Models Use Long Contexts"☆338Updated last year
- Prod Env☆414Updated last year
- MEND: Fast Model Editing at Scale☆243Updated last year
- TruthfulQA: Measuring How Models Imitate Human Falsehoods☆713Updated 3 months ago
- Training Sparse Autoencoders on Language Models☆724Updated this week
- ☆264Updated last year
- Aligning Large Language Models with Human: A Survey☆724Updated last year
- Sparsify transformers with SAEs and transcoders☆515Updated this week
- All available datasets for Instruction Tuning of Large Language Models☆248Updated last year