aviclu / ffn-valuesLinks
☆66Updated 2 years ago
Alternatives and similar repositories for ffn-values
Users that are interested in ffn-values are comparing it to the libraries listed below
Sorting:
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆97Updated 4 years ago
- ☆98Updated last year
- Inspecting and Editing Knowledge Representations in Language Models☆117Updated 2 years ago
- ☆86Updated 2 years ago
- ☆44Updated last year
- Semi-Parametric Editing with a Retrieval-Augmented Counterfactual Model☆68Updated 2 years ago
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…☆61Updated 2 years ago
- ☆45Updated last year
- Augmenting Statistical Models with Natural Language Parameters☆28Updated last year
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆39Updated 2 years ago
- ☆75Updated last year
- [EMNLP 2022] TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models☆74Updated last year
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆80Updated last year
- ☆112Updated 3 years ago
- ☆78Updated 2 years ago
- [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training☆22Updated last year
- ☆54Updated 2 years ago
- ☆54Updated last year
- Github repository for "FELM: Benchmarking Factuality Evaluation of Large Language Models" (NeurIPS 2023)☆59Updated last year
- Repo for the paper "Large Language Models Struggle to Learn Long-Tail Knowledge"☆78Updated 2 years ago
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆78Updated 2 years ago
- contrastive decoding☆202Updated 2 years ago
- Code for Editing Factual Knowledge in Language Models☆141Updated 3 years ago
- ☆22Updated 2 years ago
- Restore safety in fine-tuned language models through task arithmetic☆29Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- ☆46Updated last year
- Codebase for Hyperdecoders https://arxiv.org/abs/2203.08304☆13Updated 3 years ago
- MEND: Fast Model Editing at Scale☆251Updated 2 years ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆82Updated 7 months ago