Show HN: Steiner – An open-source reasoning model inspired by OpenAI o1 https://ift.tt/oOLniVF
Show HN: Steiner – An open-source reasoning model inspired by OpenAI o1 Steiner is a series of reasoning models trained on synthetic data using reinforcement learning. These models can explore multiple reasoning paths in an autoregressive manner during inference and autonomously verify or backtrack when necessary, enabling a linear traversal of the implicit search tree. Blog: https://ift.tt/XGtYzLk... Hugging Face: https://ift.tt/2CUtvOY... https://ift.tt/S7Z2VJe October 22, 2024 at 11:07PM
Komentar
Posting Komentar