(medium.com)

68 points peakji | 2 comments | 22 Oct 24 16:07 UTC | HN request time: 0s | source

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...

1. schmeichel ◴[22 Oct 24 19:14 UTC] No.41917645[source]▶

>>41915735 (OP) #

This seems promising! Great work! Any chance there will be a Ollama Modelfile for the masses?

replies(1): >>41917682 #

2. peakji ◴[22 Oct 24 19:18 UTC] No.41917682[source]▶

>>41917645 (TP) #

GGUF files are available on HF: https://huggingface.co/peakji/steiner-32b-preview-gguf

I haven't personally used Ollama Modelfile, but I think it should be relatively easy to convert from GGUF?

↑

Show HN: Steiner – An open-source reasoning model inspired by OpenAI o1