ContextualAI / HALOsLinks
A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
☆873Updated 2 weeks ago
Alternatives and similar repositories for HALOs
Users that are interested in HALOs are comparing it to the libraries listed below
Sorting:
- RewardBench: the first evaluation tool for reward models.☆619Updated last month
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆912Updated 5 months ago
- Official repository for ORPO☆460Updated last year
- The official implementation of Self-Play Fine-Tuning (SPIN)☆1,181Updated last year
- [ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data …☆736Updated 4 months ago
- Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"☆504Updated 6 months ago
- ☆525Updated 8 months ago
- Code for Quiet-STaR☆735Updated 11 months ago
- ☆857Updated 3 weeks ago
- This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.☆546Updated last year
- Generative Representational Instruction Tuning☆662Updated last month
- [COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition☆645Updated last year
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆626Updated last year
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆474Updated 9 months ago
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆739Updated 10 months ago
- Scalable toolkit for efficient model alignment☆833Updated this week
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆818Updated last year
- Recipes to scale inference-time compute of open models☆1,110Updated 2 months ago
- Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).☆769Updated 2 years ago
- A curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval.☆370Updated last year
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆561Updated 7 months ago
- Representation Engineering: A Top-Down Approach to AI Transparency☆852Updated 11 months ago
- Codebase for Merging Language Models (ICML 2024)☆842Updated last year
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆468Updated last year
- Pytorch implementation of DoReMi, a method for optimizing the data mixture weights in language modeling datasets☆340Updated last year
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆539Updated 6 months ago
- A bibliography and survey of the papers surrounding o1☆1,207Updated 8 months ago
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning☆397Updated last year
- Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI☆1,394Updated last year
- Code and data for "Lost in the Middle: How Language Models Use Long Contexts"☆352Updated last year