| license: mit | |
| language: | |
| - en | |
| base_model: | |
| - meta-llama/Meta-Llama-3-8B | |
| This is the trained skill LoRA for the HotpotQA dataset in the paper [Fictitious Synthetic Data Can Improve LLM Factuality via Prerequisite Learning](https://arxiv.org/pdf/2410.19290). | |