neelsjain / NEFTune
Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning
☆366Updated 4 months ago
Related projects: ⓘ
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆467Updated 3 months ago
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆416Updated 6 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆539Updated 6 months ago
- Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets☆292Updated 8 months ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆333Updated last month
- ☆239Updated 10 months ago
- A large-scale, fine-grained, diverse preference dataset (and models).☆299Updated 8 months ago
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆572Updated last month
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆337Updated 2 months ago
- Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"☆405Updated 4 months ago
- SimPO: Simple Preference Optimization with a Reference-Free Reward☆648Updated 3 weeks ago
- Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality s…☆398Updated this week
- Generative Representational Instruction Tuning☆527Updated 2 weeks ago
- DSIR large-scale data selection framework for language model training☆221Updated 5 months ago
- Rectified Rotary Position Embeddings☆329Updated 4 months ago
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆508Updated 6 months ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆244Updated last week
- [EMNLP 2023] Adapting Language Models to Compress Long Contexts☆268Updated last week
- Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.☆290Updated 5 months ago
- RewardBench: the first evaluation tool for reward models.☆352Updated last week
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆695Updated last week
- ☆284Updated 3 months ago
- [ACL'24 Outstanding] Data and code for L-Eval, a comprehensive long context language models evaluation benchmark☆342Updated 2 months ago
- All available datasets for Instruction Tuning of Large Language Models☆231Updated 9 months ago
- Generative Judge for Evaluating Alignment☆208Updated 8 months ago
- [ACL 2024] Progressive LLaMA with Block Expansion.☆464Updated 3 months ago
- LongAlign: A Recipe for Long Context Alignment Encompassing Data, Training, and Evaluation☆194Updated 4 months ago
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆196Updated last year
- Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models☆208Updated last week
- Official repository for ORPO☆409Updated 3 months ago