metadata
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.
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.