Instructions to use MindscapeRAG/MiA-Emb-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MindscapeRAG/MiA-Emb-8B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="MindscapeRAG/MiA-Emb-8B")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MindscapeRAG/MiA-Emb-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Create README.md
Browse files
README.md
CHANGED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
## Transformer Usage
|
| 2 |
+
Coming Soon!
|
| 3 |
+
|
| 4 |
+
## Citation
|
| 5 |
+
|
| 6 |
+
If you find this work useful, please cite:
|
| 7 |
+
|
| 8 |
+
```bibtex
|
| 9 |
+
@misc{li2025mindscapeawareretrievalaugmentedgeneration,
|
| 10 |
+
title={Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding},
|
| 11 |
+
author={Yuqing Li and Jiangnan Li and Zheng Lin and Ziyan Zhou and Junjie Wu and Weiping Wang and Jie Zhou and Mo Yu},
|
| 12 |
+
year={2025},
|
| 13 |
+
eprint={2512.17220},
|
| 14 |
+
archivePrefix={arXiv},
|
| 15 |
+
primaryClass={cs.CL},
|
| 16 |
+
url={https://arxiv.org/abs/2512.17220},
|
| 17 |
+
}
|
| 18 |
+
```
|