Prereq-Tune_Models
Collection
Trained models for the Prereq-Tune paper • 4 items • Updated
This is the trained skill LoRA for the HotpotQA dataset in the paper Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Shiyu-Lab/Prereq-Tune_hotpotqa
Base model
meta-llama/Meta-Llama-3-8B