magpie-align / magpieLinks
[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!
☆782Updated 7 months ago
Alternatives and similar repositories for magpie
Users that are interested in magpie are comparing it to the libraries listed below
Sorting:
- Large Reasoning Models☆805Updated 10 months ago
- ☆971Updated 3 months ago
- ☆963Updated 9 months ago
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆923Updated 8 months ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆572Updated 10 months ago
- FuseAI Project☆583Updated 9 months ago
- Official repository for ORPO☆463Updated last year
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆747Updated last year
- ☆544Updated 11 months ago
- An Open Source Toolkit For LLM Distillation☆744Updated 3 months ago
- ☆312Updated last year
- [ACL 2024] Progressive LLaMA with Block Expansion.☆510Updated last year
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆477Updated last year
- [ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning☆362Updated last year
- LongBench v2 and LongBench (ACL 25'&24')☆997Updated 9 months ago
- A series of technical report on Slow Thinking with LLM☆744Updated 2 months ago
- RewardBench: the first evaluation tool for reward models.☆643Updated 4 months ago
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆890Updated 3 weeks ago
- An Open Large Reasoning Model for Real-World Solutions☆1,522Updated 4 months ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆440Updated last year
- Generative Representational Instruction Tuning☆675Updated 4 months ago
- Codebase for Merging Language Models (ICML 2024)☆853Updated last year
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆631Updated last year
- ☆548Updated 9 months ago
- Automatic evals for LLMs☆547Updated 3 months ago
- ☆560Updated 2 years ago
- ☆964Updated 8 months ago
- OLMoE: Open Mixture-of-Experts Language Models☆888Updated last month
- Scalable toolkit for efficient model alignment☆841Updated 2 weeks ago
- ⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)☆994Updated 10 months ago