mega002 / lm-debugger
The official code of LM-Debugger, an interactive tool for inspection and intervention in transformer-based language models.
☆177Updated 2 years ago
Alternatives and similar repositories for lm-debugger:
Users that are interested in lm-debugger are comparing it to the libraries listed below
- A library for finding knowledge neurons in pretrained transformer models.☆155Updated 3 years ago
- A framework for few-shot evaluation of autoregressive language models.☆103Updated last year
- ☆65Updated last year
- The original implementation of Min et al. "Nonparametric Masked Language Modeling" (paper https//arxiv.org/abs/2212.01349)☆157Updated 2 years ago
- Inspecting and Editing Knowledge Representations in Language Models☆114Updated last year
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆90Updated 3 years ago
- PyTorch + HuggingFace code for RetoMaton: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022), including an…☆270Updated 2 years ago
- The official code of EMNLP 2022, "SCROLLS: Standardized CompaRison Over Long Language Sequences".☆69Updated last year
- Tk-Instruct is a Transformer model that is tuned to solve many NLP tasks by following instructions.☆179Updated 2 years ago
- This project studies the performance and robustness of language models and task-adaptation methods.☆149Updated 10 months ago
- Utilities for the HuggingFace transformers library☆67Updated 2 years ago
- ☆46Updated last year
- ☆129Updated 2 months ago
- How do transformer LMs encode relations?☆46Updated last year
- What's In My Big Data (WIMBD) - a toolkit for analyzing large text datasets☆215Updated 4 months ago
- ☆54Updated last year
- This repository accompanies our paper “Do Prompt-Based Models Really Understand the Meaning of Their Prompts?”☆85Updated 2 years ago
- Code for paper "CrossFit : A Few-shot Learning Challenge for Cross-task Generalization in NLP" (https://arxiv.org/abs/2104.08835)☆110Updated 2 years ago
- Pipeline for pulling and processing online language model pretraining data from the web☆177Updated last year
- Sparse probing paper full code.☆55Updated last year
- ☆97Updated 2 years ago
- A library for parameter-efficient and composable transfer learning for NLP with sparse fine-tunings.☆71Updated 7 months ago
- Interpretability for sequence generation models 🐛 🔍☆410Updated 4 months ago
- ☆38Updated 11 months ago
- ☆72Updated last year
- Interpreting Language Models with Contrastive Explanations (EMNLP 2022 Best Paper Honorable Mention)☆62Updated 2 years ago
- The LM Contamination Index is a manually created database of contamination evidences for LMs.☆78Updated 11 months ago
- A unified benchmark for math reasoning☆87Updated 2 years ago
- [Data + code] ExpertQA : Expert-Curated Questions and Attributed Answers☆126Updated last year
- PAIR.withgoogle.com and friend's work on interpretability methods☆173Updated this week