Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)
☆59May 12, 2025Updated last year
Alternatives and similar repositories for GEM
Users that are interested in GEM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for Blog Post: Can Better Cold-Start Strategies Improve RL Training for LLMs?☆20Mar 9, 2025Updated last year
- ☆19Oct 30, 2025Updated 10 months ago
- ☆15Jan 27, 2025Updated last year
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)☆29Dec 19, 2023Updated 2 years ago
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).☆17Jan 8, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ACL'25] Official code of curiosity-driven RLHF☆16Jun 22, 2025Updated last year
- Official Repository of "Learning what reinforcement learning can't"☆86Dec 30, 2025Updated 8 months ago
- [ICLR 2026] PSFT is a trust-region–inspired fine-tuning objective that views SFT as a policy gradient method with constant advantages, co…☆39Sep 9, 2025Updated 11 months ago
- This repository contains the replication of the iGSM dataset generation process from the Physics of LLM paper by Zeyuan Zhu.☆17Sep 13, 2024Updated last year
- ☆73Oct 23, 2025Updated 10 months ago
- Code and data used in the paper: "Training on Incorrect Synthetic Data via RL Scales LLM Math Reasoning Eight-Fold"☆32Jun 16, 2024Updated 2 years ago
- This repo explores how AMR to address tasks difficult for LLMs☆12Jan 15, 2024Updated 2 years ago
- ☆16Jun 10, 2025Updated last year
- Reproduced the DFT method without using Verl. https://arxiv.org/abs/2508.05629☆24Oct 14, 2025Updated 10 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆34Jul 11, 2024Updated 2 years ago
- [NeurIPS-2023] The PyTorch Implementation of MoSo. The algorithms are based on our paper: "Data Pruning via Moving-one-Sample-out". MoSo …☆10May 21, 2026Updated 3 months ago
- ☆47Jun 24, 2025Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Jan 17, 2024Updated 2 years ago
- An Efficient Dataset Condensation Plugin and Its Application to Continual Learning. NeurIPS, 2023.☆12Nov 29, 2023Updated 2 years ago
- Code implementation of synthetic continued pretraining☆162Jan 6, 2025Updated last year
- ☆18Feb 2, 2026Updated 7 months ago
- [ACL 2025, Main Conference, Oral] Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process☆30Aug 2, 2024Updated 2 years ago
- Official Repo for DAC-RL: Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability☆16Feb 26, 2026Updated 6 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆18Mar 3, 2025Updated last year
- Multi-Task instruction-tuned LLaMA☆14May 5, 2023Updated 3 years ago
- This repo contains the code for the paper "Understanding and Mitigating Hallucinations in Large Vision-Language Models via Modular Attrib…☆39Jul 14, 2025Updated last year
- ☆83Jun 8, 2026Updated 2 months ago
- Explore, Establish, Exploit: Red Teaming Language Models from Scratch☆15Jun 21, 2023Updated 3 years ago
- 基于PyTorch GPT-2的针对各种数据并行pretrain的研究代码.☆11Dec 16, 2022Updated 3 years ago
- The loss landscape of Large Language Models resemble basin!☆45Jul 8, 2025Updated last year
- [NeurIPS 2025] Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"☆168Mar 2, 2026Updated 6 months ago
- Data Efficacy for Language Model Training☆52May 29, 2026Updated 3 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆21Aug 25, 2026Updated last week
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆50Jan 19, 2024Updated 2 years ago
- Code and models for EMNLP 2024 paper "WPO: Enhancing RLHF with Weighted Preference Optimization"☆41Sep 24, 2024Updated last year
- ☆35May 16, 2025Updated last year
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆466Mar 20, 2026Updated 5 months ago
- The repository contains code for Adaptive Data Optimization☆37Dec 9, 2024Updated last year
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆188Jul 23, 2025Updated last year