H4 Alignment Handbook

https://github.com/huggingface/alignment-handbook

AI & ML interests

LLM alignment

Recent Activity

lewtun submitted a paper about 23 hours ago

Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL

ybelkada authored a paper about 1 month ago

Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers

ybelkada authored a paper 7 months ago

NeurIPS 2025 E2LM Competition : Early Training Evaluation of Language Models

View all activity

alignment-handbook 's models 5

alignment-handbook/mistral-7b-sft-constitutional-ai

Text Generation • 7B • Updated Jan 31, 2024 • 21

alignment-handbook/zephyr-7b-dpo-full

Text Generation • 7B • Updated Jan 10, 2024 • 33 • 3

alignment-handbook/zephyr-7b-sft-full

Text Generation • 7B • Updated Jan 10, 2024 • 6.22k • • 27

alignment-handbook/zephyr-7b-dpo-qlora

Updated Jan 9, 2024 • 18 • 9

alignment-handbook/zephyr-7b-sft-qlora

Updated Jan 9, 2024 • 193 • 9