Back to skyworkai/skywork-reward-v2
Projects sharing features with Skywork Reward V2
24 open-source projects similar to skyworkai/skywork-reward-v2, ranked by shared indexed features. Tags may describe platforms or build tools rather than the same primary purpose. Check each project’s use case, license, and deployment requirements before treating it as a replacement.
- allenai/open-instruct
allenai/open-instruct
3,586View on GitHubOpen-Instruct is a distributed training and instruction tuning framework for large language models. It functions as a coordinator for supervised fine-tuning, reinforcement learning from human feedback pipelines, and tool-use training, providing specialized roles for dataset curation and model alignment. The project distinguishes itself through a high-performance training architecture that utilizes actor-based distributed coordination and hybrid sharding to manage large GPU clusters. It implements advanced alignment techniques including direct preference optimization, group relative policy opt
Python - ezelikman/star
ezelikman/STaR
1. STaR 2. Mesh Transformer JAX 1. Updates 3. Pretrained Models 1. GPT-J-6B 1. Links 2. Acknowledgments 3. License 4. Model Details 5. Zero-Shot Evaluations 4. Architecture and Usage 1. Fine-tuning 2. JAX Dependency 5. TODO
Python
