princeton-nlp / LESS
[ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning
☆424Updated 5 months ago
Alternatives and similar repositories for LESS:
Users that are interested in LESS are comparing it to the libraries listed below
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆542Updated 3 months ago
- RewardBench: the first evaluation tool for reward models.☆532Updated last month
- Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"☆475Updated 2 months ago
- Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets☆316Updated last year
- A series of technical report on Slow Thinking with LLM☆595Updated this week
- Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models☆251Updated 6 months ago
- ☆271Updated 2 months ago
- Repository for Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning☆161Updated last year
- [NAACL'24] Self-data filtering of LLM instruction-tuning data using a novel perplexity-based difficulty score, without using any other mo…☆347Updated 6 months ago
- A Survey on Data Selection for Language Models☆218Updated 5 months ago
- This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.☆299Updated 7 months ago
- ☆325Updated last month
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆191Updated 11 months ago
- Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"☆357Updated 2 months ago
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆246Updated last year
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning☆393Updated 10 months ago
- ☆264Updated 8 months ago
- LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment☆311Updated 10 months ago
- ☆504Updated 2 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆598Updated last year
- This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.☆511Updated 4 months ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆313Updated 6 months ago
- [EMNLP 2023] Adapting Language Models to Compress Long Contexts☆296Updated 6 months ago
- Collection of training data management explorations for large language models☆315Updated 7 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆597Updated 2 months ago
- [EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs☆247Updated 3 months ago
- Code and data for "Lost in the Middle: How Language Models Use Long Contexts"☆334Updated last year
- A large-scale, fine-grained, diverse preference dataset (and models).☆335Updated last year
- The repo for In-context Autoencoder☆117Updated 10 months ago
- ☆166Updated last month