uclaml / SPPO
The official implementation of Self-Play Preference Optimization (SPPO)
☆494Updated last month
Alternatives and similar repositories for SPPO:
Users that are interested in SPPO are comparing it to the libraries listed below
- A recipe for online RLHF and online iterative DPO.☆488Updated 2 months ago
- Recipes to train reward model for RLHF.☆1,205Updated 3 weeks ago
- The official implementation of the ICML 2024 paper "MemoryLLM: Towards Self-Updatable Large Language Models" and "M+: Extending MemoryLLM…☆124Updated 2 weeks ago
- Mulberry, an o1-like Reasoning and Reflection MLLM Implemented via Collective MCTS☆779Updated 2 weeks ago
- AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning (NeurIPS 2024)☆181Updated last week
- adds Sequence Parallelism into LLaMA-Factory☆261Updated this week
- [NeurIPS 2024] BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models☆244Updated 3 months ago
- The Official Repo of ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code (https://a…☆287Updated 3 months ago
- Benchmarking LLMs via Uncertainty Quantification☆209Updated last year
- The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models☆545Updated 3 weeks ago
- RewardBench: the first evaluation tool for reward models.☆516Updated this week
- Unified KV Cache Compression Methods for Auto-Regressive Models☆911Updated 2 months ago
- Explore concepts like Self-Correct, Self-Refine, Self-Improve, Self-Contradict, Self-Play, and Self-Knowledge, alongside o1-like reasonin…☆158Updated 2 months ago
- The official repo for paper, LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods.☆281Updated 2 months ago
- A curated list of awesome leaderboard-oriented resources for foundation models☆256Updated this week
- MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler a…☆173Updated 3 months ago
- MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models☆413Updated last year
- ☆374Updated 2 months ago
- The codes about "Uni-MoE: Scaling Unified Multimodal Models with Mixture of Experts"☆694Updated last month
- 🌾 OAT: A research-friendly framework for LLM online alignment, including preference learning, reinforcement learning, etc.☆210Updated last week
- The repository for the paper titled "Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks"☆153Updated 2 months ago
- APOLLO: SGD-like Memory, AdamW-level Performance☆172Updated last week
- [ICLR 2025] The official implementation of our ICLR2025 paper "AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak…☆216Updated last month
- [ECCV 2024] Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?☆153Updated 5 months ago
- Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models☆170Updated 4 months ago
- Official repository for ICLR 2025 paper "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient an…☆638Updated 2 weeks ago
- The official evaluation suite and dynamic data release for MixEval.☆231Updated 3 months ago