princeton-nlp / AutoCompressorsLinks
[EMNLP 2023] Adapting Language Models to Compress Long Contexts
☆318Updated last year
Alternatives and similar repositories for AutoCompressors
Users that are interested in AutoCompressors are comparing it to the libraries listed below
Sorting:
- [ACL'24 Outstanding] Data and code for L-Eval, a comprehensive long context language models evaluation benchmark☆391Updated last year
- DSIR large-scale data selection framework for language model training☆266Updated last year
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆478Updated last year
- ACL 2024 | LooGLE: Long Context Evaluation for Long-Context Language Models☆192Updated last year
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆356Updated last year
- Code and data for "Lost in the Middle: How Language Models Use Long Contexts"☆365Updated last year
- Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"☆524Updated 10 months ago
- Generative Judge for Evaluating Alignment☆248Updated last year
- Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets☆347Updated last year
- ☆272Updated 2 years ago
- ☆294Updated last year
- open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality☆222Updated last year
- ☆313Updated last year
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]☆110Updated 9 months ago
- Benchmarking LLMs with Challenging Tasks from Real Users☆246Updated last year
- Data and Code for Program of Thoughts [TMLR 2023]☆292Updated last year
- Datasets for Instruction Tuning of Large Language Models☆259Updated 2 years ago
- ☆315Updated last year
- ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings - NeurIPS 2023 (oral)☆264Updated last year
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆443Updated last year
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆552Updated last year
- [ICML 2024] Selecting High-Quality Data for Training Language Models☆193Updated last year
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆240Updated 2 months ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆576Updated 11 months ago
- LOFT: A 1 Million+ Token Long-Context Benchmark☆218Updated 5 months ago
- [ACL 2024] Long-Context Language Modeling with Parallel Encodings☆167Updated last year
- [EMNLP 2023] The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning☆250Updated 2 years ago
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning☆405Updated last year
- Learning to Compress Prompts with Gist Tokens - https://arxiv.org/abs/2304.08467☆300Updated 9 months ago
- Official Repo for ICLR 2024 paper MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback by Xingyao Wang*, Ziha…☆134Updated last year