kmeng01 / memit
Mass-editing thousands of facts into a transformer memory (ICLR 2023)
☆481Updated last year
Alternatives and similar repositories for memit:
Users that are interested in memit are comparing it to the libraries listed below
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆517Updated 2 months ago
- Locating and editing factual associations in GPT (NeurIPS 2022)☆627Updated last year
- Representation Engineering: A Top-Down Approach to AI Transparency☆819Updated 8 months ago
- RewardBench: the first evaluation tool for reward models.☆555Updated last month
- [EMNLP 2023] The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning☆238Updated last year
- ☆287Updated last year
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆651Updated 10 months ago
- PaL: Program-Aided Language Models (ICML 2023)☆488Updated last year
- Learning to Compress Prompts with Gist Tokens - https://arxiv.org/abs/2304.08467☆284Updated 2 months ago
- Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"☆481Updated 3 months ago
- Landmark Attention: Random-Access Infinite Context Length for Transformers☆422Updated last year
- Code and data for "Lost in the Middle: How Language Models Use Long Contexts"☆340Updated last year
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆545Updated last year
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆628Updated 9 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆486Updated 10 months ago
- ☆270Updated 2 years ago
- [EMNLP 2023] Adapting Language Models to Compress Long Contexts☆303Updated 7 months ago
- ☆237Updated 2 years ago
- batched loras☆341Updated last year
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆452Updated last year
- DSIR large-scale data selection framework for language model training☆246Updated last year
- ☆308Updated 10 months ago
- ☆255Updated last year
- [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the dive…☆935Updated 6 months ago
- Controlled Text Generation via Language Model Arithmetic☆218Updated 7 months ago
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning☆395Updated 11 months ago
- The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction☆386Updated 9 months ago
- ☆356Updated 2 years ago
- This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large Language Models.☆463Updated last year
- This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious c…☆222Updated 2 years ago