liziniu / cold_start_rlLinks
Code for Blog Post: Can Better Cold-Start Strategies Improve RL Training for LLMs?
☆16Updated 2 months ago
Alternatives and similar repositories for cold_start_rl
Users that are interested in cold_start_rl are comparing it to the libraries listed below
Sorting:
- Codebase for Instruction Following without Instruction Tuning☆34Updated 8 months ago
- The official implementation for Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free☆38Updated 3 weeks ago
- Code for preprint "Metadata Conditioning Accelerates Language Model Pre-training (MeCo)"☆39Updated 3 weeks ago
- Revisiting Mid-training in the Era of RL Scaling☆48Updated last month
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆32Updated 2 months ago
- Suri: Multi-constraint instruction following for long-form text generation (EMNLP’24)☆22Updated 6 months ago
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆73Updated 2 weeks ago
- ☆17Updated 4 months ago
- Long Context Extension and Generalization in LLMs☆56Updated 8 months ago
- [ICLR 2025] LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization☆36Updated 3 months ago
- Exploration of automated dataset selection approaches at large scales.☆41Updated 2 months ago
- ☆22Updated 10 months ago
- ☆29Updated 5 months ago
- ☆46Updated 2 months ago
- A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models☆55Updated 3 months ago
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆62Updated 10 months ago
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆78Updated 2 weeks ago
- ☆59Updated 9 months ago
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆45Updated 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…☆31Updated 8 months ago
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆63Updated 7 months ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆47Updated last year
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆50Updated 5 months ago
- The code and data for the paper JiuZhang3.0☆45Updated last year
- A scalable automated alignment method for large language models. Resources for "Aligning Large Language Models via Self-Steering Optimiza…☆18Updated 6 months ago
- [ACL 2025] Are Your LLMs Capable of Stable Reasoning?☆25Updated 2 months ago
- [NAACL 2025] Source code for MMEvalPro, a more trustworthy and efficient benchmark for evaluating LMMs☆24Updated 8 months ago
- Official implementation of the paper "From Complex to Simple: Enhancing Multi-Constraint Complex Instruction Following Ability of Large L…☆48Updated 11 months ago
- ☆15Updated last month
- Pytorch implementation for "Compressed Context Memory For Online Language Model Interaction" (ICLR'24)☆58Updated last year