---
base_model: bert-base-uncased
library_name: peft
tags: [retrieval, rag, reinforcement-learning, lora]
---
# emb-rag-bert-relsft
LoRA adapter for **bert-base-uncased** — Relevance-SFT (direct; winner recipe). Trained on MuSiQue; see https://irisicy4.github.io/exp-record/projects/indirect-rag/