Views
No views yet
1ziv init --model code
2ziv start| Property | Value |
|---|---|
| Base model | Alibaba-NLP/gte-modernbert-base |
| Model type | Text embedding |
| Embedding dimension | 768 |
| Max sequence length | 8192 |
| Runtime | onnxruntime |
| Primary use | Semantic code search / code understanding |
| File | Description |
|---|---|
model.onnx | ONNX model weights and graph |
tokenizer.json | Tokenizer vocabulary and rules |
tokenizer_config.json | Tokenizer settings |
config.json | Model architecture config |
1_Pooling/config.json | Pooling configuration |
1@inproceedings{zhang2024mgte,
2 title={mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval},
3 author={Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Wen and Dai, Ziqi and Tang, Jialong and Lin, Huan and Yang, Baosong and Xie, Pengjun and Huang, Fei and others},
4 booktitle={Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track},
5 pages={1393--1412},
6 year={2024}
7}
8
9@article{li2023towards,
10 title={Towards general text embeddings with multi-stage contrastive learning},
11 author={Li, Zehan and Zhang, Xin and Zhang, Yanzhao and Long, Dingkun and Xie, Pengjun and Zhang, Meishan},
12 journal={arXiv preprint arXiv:2308.03281},
13 year={2023}
14}