ContextualAI / HALOs
A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
☆745Updated this week
Related projects ⓘ
Alternatives and complementary repositories for HALOs
- RewardBench: the first evaluation tool for reward models.☆436Updated 3 weeks ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆716Updated 2 weeks ago
- Official repository for ORPO☆421Updated 5 months ago
- Generative Representational Instruction Tuning☆567Updated this week
- ☆1,274Updated this week
- Codebase for Merging Language Models (ICML 2024)☆774Updated 6 months ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆498Updated 6 months ago
- Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality s…☆495Updated 2 weeks ago
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning☆384Updated 6 months ago
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆559Updated 8 months ago
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆438Updated 8 months ago
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆597Updated 4 months ago
- Code and data for "Lost in the Middle: How Language Models Use Long Contexts"☆318Updated 10 months ago
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆374Updated last month
- Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"☆429Updated 6 months ago
- Code for Quiet-STaR☆653Updated 3 months ago
- ☆453Updated this week
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆648Updated last month
- This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.☆438Updated 3 weeks ago
- [ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning☆615Updated 5 months ago
- Scalable toolkit for efficient model alignment☆623Updated this week
- A bibliography and survey of the papers surrounding o1☆780Updated last week
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆756Updated last year
- A large-scale, fine-grained, diverse preference dataset (and models).☆315Updated 10 months ago
- ☆432Updated last year
- Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets☆306Updated 10 months ago
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆782Updated 4 months ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆730Updated 3 months ago
- A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.☆317Updated last year
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆528Updated 8 months ago