This repository contains the SimCSE model used for generating text embeddings in the paper Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls. These embeddings are used to merge semantically similar states, improving the efficiency of tree search algorithms for LLM reasoning.

Code: https://github.com/Soistesimmer/Fetch

Downloads last month
4
Safetensors
Model size
355M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support