mega002 / ff-layersLinks
The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Levy. EMNLP, 2021.
☆99Updated 4 years ago
Alternatives and similar repositories for ff-layers
Users that are interested in ff-layers are comparing it to the libraries listed below
Sorting:
- Inspecting and Editing Knowledge Representations in Language Models☆119Updated 2 years ago
- ☆103Updated 2 years ago
- ☆68Updated 2 years ago
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆78Updated 2 years ago
- ☆47Updated 2 years ago
- Repo for the paper "Large Language Models Struggle to Learn Long-Tail Knowledge"☆78Updated 2 years ago
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆30Updated 11 months ago
- Grade-School Math with Irrelevant Context (GSM-IC) benchmark is an arithmetic reasoning dataset built upon GSM8K, by adding irrelevant se…☆64Updated 2 years ago
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…☆60Updated 2 years ago
- Code for the paper "A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis"☆19Updated 7 months ago
- ☆114Updated 3 years ago
- ☆99Updated last year
- ☆75Updated 2 years ago
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆48Updated 2 years ago
- ☆88Updated 3 years ago
- ☆55Updated last year
- ☆177Updated last year
- Synthetic question-answering dataset to formally analyze the chain-of-thought output of large language models on a reasoning task.☆154Updated 4 months ago
- A library for efficient patching and automatic circuit discovery.☆88Updated last month
- ☆53Updated 9 months ago
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆105Updated 2 years ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆80Updated last year
- ☆79Updated 3 years ago
- contrastive decoding☆206Updated 3 years ago
- ☆102Updated 2 years ago
- Easy-to-use MIRAGE code for faithful answer attribution in RAG applications. Paper: https://aclanthology.org/2024.emnlp-main.347/☆26Updated 10 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆190Updated 9 months ago
- [ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"☆109Updated 2 years ago
- ☆43Updated last year
- ☆58Updated 2 years ago