Steiner – An open-source reasoning model inspired by OpenAI o1
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://medium.com/@peakji/a-small-step-towards-reproducing-... Hugging Face: https://huggingface.co/collections/peakji/steiner-preview-67...
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Correct prediction on native model
Similar products
Open-source Piet Mondrian-inspired Pong
Brain-inspired, multi-level reasoning & planning AI model
The first reasoning model by Mistral AI
Xiaomi's Open Source Model, Born for Reasoning
Open-Source, Google Zanzibar Inspired Authorization Service
An open-source API built on top of OpenAI Embeddings and Pinecone
Open Cult. HN-inspired, open source, meetup.com alternative
An Open-Source Website to Track OpenAI API Cost by Model
Open-Source Library OpenAI/Azure Fallback Tool
Open Source VR headset inspired by the Oculus Rift