TristanThrush / perplexity-correlationsLinks
Simple and scalable tools for data-driven pretraining data selection.
☆28Updated 4 months ago
Alternatives and similar repositories for perplexity-correlations
Users that are interested in perplexity-correlations are comparing it to the libraries listed below
Sorting:
- Code for "Tracing Knowledge in Language Models Back to the Training Data"☆39Updated 2 years ago
- ☆55Updated 2 years ago
- ☆32Updated last year
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆47Updated 2 years ago
- Data and code for the preprint "In-Context Learning with Long-Context Models: An In-Depth Exploration"☆40Updated last year
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆78Updated 2 years ago
- ☆66Updated 2 years ago
- Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)☆29Updated last month
- ☆36Updated 2 years ago
- Language models scale reliably with over-training and on downstream tasks☆100Updated last year
- ☆22Updated 2 years ago
- ☆76Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- ☆39Updated last year
- Few-shot Learning with Auxiliary Data☆31Updated last year
- Repo for the paper "Large Language Models Struggle to Learn Long-Tail Knowledge"☆78Updated 2 years ago
- 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
- ☆43Updated 3 years ago
- ☆29Updated 8 months 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
- ☆92Updated last year
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆48Updated 11 months ago
- Benchmark API for Multidomain Language Modeling☆25Updated 3 years ago
- ☆36Updated 3 years ago
- ☆13Updated last year
- ☆112Updated 3 years ago
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆75Updated last year
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆12Updated 9 months ago
- [ACL'24 Oral] Analysing The Impact of Sequence Composition on Language Model Pre-Training☆22Updated last year