neelsjain / NEFTune
Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning
☆393Updated 9 months ago
Alternatives and similar repositories for NEFTune:
Users that are interested in NEFTune are comparing it to the libraries listed below
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆536Updated 3 months ago
- Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets☆313Updated last year
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆416Updated 4 months ago
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆617Updated 7 months ago
- ☆253Updated last year
- DSIR large-scale data selection framework for language model training☆242Updated 11 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆594Updated last year
- InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning☆243Updated last year
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆453Updated 11 months ago
- Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"☆469Updated last month
- Official repository for ORPO☆443Updated 9 months ago
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆543Updated last year
- [ACL'24] Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning☆144Updated 6 months ago
- Rectified Rotary Position Embeddings☆356Updated 9 months ago
- RewardBench: the first evaluation tool for reward models.☆521Updated 2 weeks ago
- [EMNLP 2023] Adapting Language Models to Compress Long Contexts☆294Updated 6 months ago
- Codes and Data for Scaling Relationship on Learning Mathematical Reasoning with Large Language Models☆245Updated 6 months ago
- A large-scale, fine-grained, diverse preference dataset (and models).☆331Updated last year
- Codebase for Merging Language Models (ICML 2024)☆800Updated 10 months ago
- ☆261Updated 7 months ago
- Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates☆446Updated 10 months ago
- train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism☆215Updated last year
- Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.☆405Updated 10 months ago
- A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarks☆258Updated 7 months ago
- Code and data for "Lost in the Middle: How Language Models Use Long Contexts"☆334Updated last year
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆392Updated 4 months ago
- ☆500Updated 3 months ago
- 🐋 An unofficial implementation of Self-Alignment with Instruction Backtranslation.☆137Updated 8 months ago
- [EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs☆241Updated 2 months ago
- Generative Representational Instruction Tuning☆606Updated last month