abacusai / smaugLinks
☆79Updated last year
Alternatives and similar repositories for smaug
Users that are interested in smaug are comparing it to the libraries listed below
Sorting:
- Self-Alignment with Principle-Following Reward Models☆169Updated last month
- Directional Preference Alignment☆57Updated last year
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆75Updated 5 months ago
- Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]☆149Updated last year
- ☆107Updated 3 months ago
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]☆109Updated 8 months ago
- Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]☆143Updated last year
- Reproduction of "RLCD Reinforcement Learning from Contrast Distillation for Language Model Alignment☆69Updated 2 years ago
- Large Language Models Can Self-Improve in Long-context Reasoning☆73Updated 11 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆112Updated 9 months ago
- ☆77Updated 7 months ago
- [ICLR 2024] CLEX: Continuous Length Extrapolation for Large Language Models☆78Updated last year
- B-STAR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners☆86Updated 5 months ago
- RM-R1: Unleashing the Reasoning Potential of Reward Models☆146Updated 4 months ago
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆66Updated 8 months ago
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆83Updated 7 months ago
- The official repository of "Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint"☆38Updated last year
- Reference implementation for Token-level Direct Preference Optimization(TDPO)☆148Updated 8 months ago
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆57Updated last year
- Repo of paper "Free Process Rewards without Process Labels"☆165Updated 7 months ago
- This is an official implementation of the Reward rAnked Fine-Tuning Algorithm (RAFT), also known as iterative best-of-n fine-tuning or re…☆37Updated last year
- [NeurIPS 2024] OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI☆108Updated 8 months ago
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"☆41Updated last year
- Code for ACL2024 paper - Adversarial Preference Optimization (APO).☆57Updated last year
- ☆103Updated last year
- ☆57Updated 5 months ago
- [ACL 2025] An inference-time decoding strategy with adaptive foresight sampling☆106Updated 5 months ago
- ☆100Updated last year
- Source code of "Reasons to Reject? Aligning Language Models with Judgments"☆58Updated last year
- Reformatted Alignment☆112Updated last year