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!
☆705Updated 2 months ago
Alternatives and similar repositories for magpie
Users that are interested in magpie are comparing it to the libraries listed below
Sorting:
- Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.☆727Updated 8 months ago
- ☆731Updated last month
- [ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning☆353Updated 8 months ago
- Official repository for ORPO☆453Updated last year
- [NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward☆896Updated 3 months ago
- Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]☆555Updated 5 months ago
- Large Reasoning Models☆803Updated 6 months ago
- ☆283Updated 10 months ago
- ☆934Updated 4 months ago
- RewardBench: the first evaluation tool for reward models.☆590Updated this week
- Implementation of paper Data Engineering for Scaling Language Models to 128K Context☆462Updated last year
- Generative Representational Instruction Tuning☆640Updated 2 months ago
- LongBench v2 and LongBench (ACL 2024)☆888Updated 4 months ago
- ☆517Updated 6 months ago
- An Open Source Toolkit For LLM Distillation☆618Updated this week
- [ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning☆612Updated last year
- A series of technical report on Slow Thinking with LLM☆685Updated this week
- Scalable toolkit for efficient model alignment☆807Updated this week
- ☆540Updated 5 months ago
- FuseAI Project☆570Updated 4 months ago
- Code for Quiet-STaR☆732Updated 9 months ago
- [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"☆410Updated 7 months ago
- ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)☆631Updated 4 months ago
- Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning☆396Updated last year
- A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).☆851Updated last week
- [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning☆453Updated 7 months ago
- [ACL 2024] Progressive LLaMA with Block Expansion.☆502Updated last year
- ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning☆888Updated 2 weeks ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,040Updated this week
- [ICML 2025] Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale☆248Updated 3 weeks ago