Gen-Verse/dLLM-RL

Framework for reinforcement learning on diffusion language models

View on index · View in 3D Map

Related repos

• Unifies training and evaluation of diffusion language models
• Reinforcement learning framework for language agents
• open-source reinforcement learning for language models
• Diffusion-based code generation language model
• reinforcement learning library for training large language models, supports many RL algorithms, integrates with LLM tools, scales to models with up to 671B parameters
• Large language model using diffusion for text generation
• Scripts and tools for training and fine-tuning Stable Diffusion models
• control diffusion models with extra conditions for image generation
• open-source large language model for reasoning, coding, and agents
• vision-language model using reinforcement learning for visual understanding tasks