How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
๐ Reinforcement Learning for Language Agents๐
The main features of agentica-project/rllm are: Reasoning Datasets, Reasoning Models, Reinforcement Learning Frameworks.
Projects with overlapping indexed features include: open-reasoner-zero/open-reasoner-zero โ An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model. inclusionai/areal โ AReaL is a system for agent orchestration, distributed model training, and parameter-efficient tuning. It provides aโฆ deep-agent/r1-v. gair-nlp/limo โ ๐ Paper | ๐ Dataset (v2) | ๐ Model (v2). hiyouga/easyr1 โ EasyR1 is a distributed model training system and reinforcement learning framework for large language andโฆ huggingface/open-r1 โ Open-r1 is a framework designed for the large-scale training, distillation, and optimization of language modelsโฆ
An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
EasyR1 is a distributed model training system and reinforcement learning framework for large language and vision-language models. It functions as a multimodal trainer and an implementation of a Proximal Policy Optimization pipeline designed to refine the reasoning and perception capabilities of models that process both text and images. The system specializes in distributing reinforcement learning workloads across multiple compute nodes to manage high memory requirements. It optimizes hardware utilization through padding-free training and fine-tuning to fit large models onto available graphics
