alibaba / ROLLLinks
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
☆1,888Updated 2 weeks ago
Alternatives and similar repositories for ROLL
Users that are interested in ROLL are comparing it to the libraries listed below
Sorting:
- Distributed RL System for LLM Reasoning☆2,569Updated this week
- Official Repo for Open-Reasoner-Zero☆2,033Updated 3 months ago
- slime is a LLM post-training framework for RL Scaling.☆1,747Updated this week
- An Open-source RL System from ByteDance Seed and Tsinghua AIR☆1,537Updated 4 months ago
- OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models☆1,818Updated 7 months ago
- Reproduce R1 Zero on Logic Puzzle☆2,396Updated 5 months ago
- A very simple GRPO implement for reproducing r1-like LLM thinking.☆1,320Updated last month
- A Survey of Reinforcement Learning for Large Reasoning Models☆1,044Updated this week
- Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning☆789Updated last month
- ☆741Updated last week
- ☆814Updated 3 months ago
- EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL☆3,552Updated last week
- Latest Advances on System-2 Reasoning☆1,231Updated 3 months ago
- VeOmni: Scaling any Modality Model Training to any Accelerators with PyTorch native Training Framework☆1,050Updated 2 weeks ago
- The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.☆1,341Updated this week
- minimal-cost for training 0.5B R1-Zero☆768Updated 4 months ago
- RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.☆2,279Updated last week
- A series of technical report on Slow Thinking with LLM☆729Updated last month
- Scalable RL solution for advanced reasoning of language models☆1,716Updated 5 months ago
- O1 Replication Journey☆1,996Updated 8 months ago
- Large Reasoning Models☆805Updated 9 months ago
- ☆921Updated 2 months ago
- verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in…☆858Updated last week
- ☆546Updated 8 months ago
- ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning☆1,175Updated 3 months ago
- Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.☆818Updated 4 months ago
- Super-Efficient RLHF Training of LLMs with Parameter Reallocation☆313Updated 4 months ago
- R1-searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning☆630Updated last month
- A fork to add multimodal model training to open-r1☆1,387Updated 7 months ago
- Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (…☆330Updated this week