README.md

---
datasets:
- tdro-llm/finetune_data
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
base_model:
- Qwen/Qwen1.5-1.8B
---

# s2-tdro-Qwen1.5-1.8B-top70

[Arxiv](https://arxiv.org/abs/2408.10613) | [Github](https://github.com/tdro-llm/tdro)


[tDRO: Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval](https://arxiv.org/abs/2408.10613). Guangyuan Ma, Yongliang Ma, Xing Wu, Zhenpeng Su, Ming Zhou and Songlin Hu.


This is a fine-tuned **tDRO optimized retriever** with **Dataset Selection Top-70%** of [tdro-llm/finetune_data](https://huggingface.co/datasets/tdro-llm/finetune_data).