Upload folder using huggingface_hub

README.md

@@ -201,28 +201,13 @@ print(scores.tolist())
 If you find this repository useful, please consider giving a star :star: and citation
 
 ```
-@article{bge-llm,
-  title={Making text embedders few-shot learners},
-  author={Li, Chaofan and Qin, MingHao and Xiao, Shitao and Chen, Jianlyu and Luo, Kun and Shao, Yingxia and Lian, Defu and Liu, Zheng},
-  journal={arXiv preprint arXiv:2409.15700},
-  year={2024}
-}
-
-@misc{bge-m3,
-      title={BGE M3-Embedding: Multi-Lingual, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation}, 
-      author={Jianlv Chen and Shitao Xiao and Peitian Zhang and Kun Luo and Defu Lian and Zheng Liu},
-      year={2024},
-      eprint={2402.03216},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL}
-}
-
-@misc{bge_embedding,
-      title={C-Pack: Packaged Resources To Advance General Chinese Embedding}, 
-      author={Shitao Xiao and Zheng Liu and Peitian Zhang and Niklas Muennighoff},
-      year={2023},
-      eprint={2309.07597},
-      archivePrefix={arXiv},
-      primaryClass={cs.CL}
+@misc{bge_code,
+    title={Towards A Generalist Code Embedding Model Based On Massive Data Synthesis}, 
+    author={Chaofan Li and Jianlyu Chen and Yingxia Shao and Defu Lian and Zheng Liu},
+    year={2025},
+    eprint={2505.12697},
+    archivePrefix={arXiv},
+    primaryClass={cs.IR},
+    url={https://arxiv.org/abs/2505.12697}, 
 }
 ```

sentence_bert_config.json

@@ -1,4 +1,4 @@
 {
-  "max_seq_length": 256,
+  "max_seq_length": 32768,
   "do_lower_case": false
 }