Unclaimed project
Are you a maintainer of verl? Claim this project to take control of your public changelog and roadmap.
Changelog
verl: Volcano Engine Reinforcement Learning for LLMs
Last updated about 1 month ago
Introduce two new experimental recipes, which will be gradually merge to main in future release.
finalize_model_grads_func in megatron model engineactor_rollout_ref.critic is not correct by @HollowMan6 in https://github.com/volcengine/verl/pull/3778data.seed to config by @HollowMan6 in https://github.com/volcengine/verl/pull/3815max_response_length - overlong_buffer.len by @bzantium in https://github.com/volcengine/verl/pull/3856kl_ctrl and fused_kernel_options configs by @HollowMan6 in https://github.com/volcengine/verl/pull/3917verl.utils.metric to import reduce_metrics by @HollowMan6 in https://github.com/volcengine/verl/pull/3927WANDB_API_KEY in code by @HollowMan6 in https://github.com/volcengine/verl/pull/3956compileall pre-commit hook checks and improve code quality by @HollowMan6 in https://github.com/volcengine/verl/pull/3946Full Changelog: https://github.com/volcengine/verl/compare/v0.6.0...v0.6.1
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Stable Diffusion web UI
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
A feature-rich command-line audio/video downloader