Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls
Paper • 2502.11183 • Published
How to use xmu-nlp/simcse-large-gsm8k with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("feature-extraction", model="xmu-nlp/simcse-large-gsm8k") # Load model directly
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("xmu-nlp/simcse-large-gsm8k")
model = AutoModel.from_pretrained("xmu-nlp/simcse-large-gsm8k", device_map="auto")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.