MikaStars39 / PeRLLinks
PeRL: Parameter-Efficient Reinforcement Learning
☆68Updated last week
Alternatives and similar repositories for PeRL
Users that are interested in PeRL are comparing it to the libraries listed below
Sorting:
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆42Updated last month
- FROM $f(x)$ AND $g(x)$ TO $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones☆57Updated this week
- ☆71Updated last year
- ☆63Updated 7 months ago
- Long Context Extension and Generalization in LLMs☆62Updated last year
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation☆75Updated 8 months ago
- Exploration of automated dataset selection approaches at large scales.☆52Updated 10 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains [NeurIPS25]☆214Updated 2 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆182Updated 6 months ago
- [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆68Updated 9 months ago
- ☆110Updated 4 months ago
- [NeurIPS-2024] 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623☆89Updated last year
- [ICML 2025] Predictive Data Selection: The Data That Predicts Is the Data That Teaches☆60Updated 10 months ago
- ☆80Updated 10 months ago
- PostTrainBench measures how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours☆127Updated this week
- [ACL 2025] Are Your LLMs Capable of Stable Reasoning?☆32Updated 5 months ago
- Code for paper "Patch-Level Training for Large Language Models"☆97Updated 2 months ago
- ☆91Updated last year
- Research work aimed at addressing the problem of modeling infinite-length context☆44Updated last month
- [ICLR 2026] RPG: KL-Regularized Policy Gradient (https://arxiv.org/abs/2505.17508)☆64Updated this week
- Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization☆81Updated last month
- ☆50Updated 11 months ago
- ☆85Updated 2 months ago
- Code and training scripts for FlexOlmo☆122Updated last week
- The evaluation framework for training-free sparse attention in LLMs☆114Updated this week
- Defeating the Training-Inference Mismatch via FP16☆180Updated 2 months ago
- ☆112Updated last year
- Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient☆64Updated 5 months ago
- ☆98Updated 3 weeks ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆61Updated last year