SalesforceAIResearch / PretrainRL-pipelineLinks
An automated data pipeline scaling RL to pretraining levels
☆71Updated last month
Alternatives and similar repositories for PretrainRL-pipeline
Users that are interested in PretrainRL-pipeline are comparing it to the libraries listed below
Sorting:
- [ACL 2025] Are Your LLMs Capable of Stable Reasoning?☆31Updated 3 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated last year
- Codebase for Instruction Following without Instruction Tuning☆36Updated last year
- ☆24Updated last year
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆40Updated last month
- ☆90Updated 2 weeks ago
- [COLM 2025] "C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing"☆18Updated 7 months ago
- ☆51Updated 9 months ago
- Verifiers for LLM Reinforcement Learning☆79Updated 7 months ago
- ☆41Updated 6 months ago
- Exploration of automated dataset selection approaches at large scales.☆50Updated 8 months ago
- SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Model https://arxiv.org/pdf/2411.02433☆111Updated 11 months ago
- ☆51Updated 6 months ago
- ☆29Updated 3 weeks ago
- A repository for research on medium sized language models.☆78Updated last year
- ☆33Updated 10 months ago
- This is the oficial repository for "Safer-Instruct: Aligning Language Models with Automated Preference Data"☆17Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- [EMNLP'25 Industry] Repo for "Z1: Efficient Test-time Scaling with Code"☆67Updated 7 months ago
- ☆16Updated last year
- The repository contains code for Adaptive Data Optimization☆28Updated 11 months ago
- [NAACL 2025] A Closer Look into Mixture-of-Experts in Large Language Models☆55Updated 9 months ago
- Code for Paper: Harnessing Webpage Uis For Text Rich Visual Understanding☆53Updated 11 months ago
- ReBase: Training Task Experts through Retrieval Based Distillation☆29Updated 9 months ago
- Tree prompting: easy-to-use scikit-learn interface for improved prompting.☆40Updated 2 years ago
- [ACL 2025] Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems☆112Updated 5 months ago
- [Technical Report] Official PyTorch implementation code for realizing the technical part of Phantom of Latent representing equipped with …☆61Updated last year
- [NeurIPS 2024 Main Track] Code for the paper titled "Instruction Tuning With Loss Over Instructions"☆38Updated last year
- ☆19Updated 10 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆92Updated last year