Upload folder using huggingface_hub
Browse files- 0_StaticEmbedding/model.safetensors +3 -0
- 0_StaticEmbedding/tokenizer.json +0 -0
- README.md +92 -0
- config_sentence_transformers.json +10 -0
- modules.json +8 -0
0_StaticEmbedding/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0c60b3d2952fb89e67a063ac4aa558ff4b02facaac5fd674d637b9e2c52ccca
|
| 3 |
+
size 134217824
|
0_StaticEmbedding/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
README.md
ADDED
|
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- ja
|
| 4 |
+
- en
|
| 5 |
+
license: mit
|
| 6 |
+
tags:
|
| 7 |
+
- sentence-transformers
|
| 8 |
+
- sentence-similarity
|
| 9 |
+
- feature-extraction
|
| 10 |
+
- generated_from_trainer
|
| 11 |
+
- dataset_size:16897699
|
| 12 |
+
- loss:MatryoshkaLoss
|
| 13 |
+
- loss:MultipleNegativesRankingLoss
|
| 14 |
+
datasets:
|
| 15 |
+
- sentence-transformers/msmarco-co-condenser-margin-mse-sym-mnrl-mean-v1
|
| 16 |
+
- sentence-transformers/squad
|
| 17 |
+
- sentence-transformers/all-nli
|
| 18 |
+
- sentence-transformers/trivia-qa
|
| 19 |
+
- nthakur/swim-ir-monolingual
|
| 20 |
+
- sentence-transformers/miracl
|
| 21 |
+
- sentence-transformers/mr-tydi
|
| 22 |
+
- hotchpotch/sentence_transformer_japanese
|
| 23 |
+
library_name: sentence-transformers
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
### Framework Versions
|
| 27 |
+
- Python: 3.12.7
|
| 28 |
+
- Sentence Transformers: 3.3.1
|
| 29 |
+
- Transformers: 4.48.0
|
| 30 |
+
- PyTorch: 2.5.1+cu124
|
| 31 |
+
- Accelerate: 1.3.0
|
| 32 |
+
- Datasets: 3.2.0
|
| 33 |
+
- Tokenizers: 0.21.0
|
| 34 |
+
|
| 35 |
+
## Citation
|
| 36 |
+
|
| 37 |
+
### BibTeX
|
| 38 |
+
|
| 39 |
+
#### Sentence Transformers
|
| 40 |
+
```bibtex
|
| 41 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 42 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 43 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 44 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 45 |
+
month = "11",
|
| 46 |
+
year = "2019",
|
| 47 |
+
publisher = "Association for Computational Linguistics",
|
| 48 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 49 |
+
}
|
| 50 |
+
```
|
| 51 |
+
|
| 52 |
+
#### MatryoshkaLoss
|
| 53 |
+
```bibtex
|
| 54 |
+
@misc{kusupati2024matryoshka,
|
| 55 |
+
title={Matryoshka Representation Learning},
|
| 56 |
+
author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
|
| 57 |
+
year={2024},
|
| 58 |
+
eprint={2205.13147},
|
| 59 |
+
archivePrefix={arXiv},
|
| 60 |
+
primaryClass={cs.LG}
|
| 61 |
+
}
|
| 62 |
+
```
|
| 63 |
+
|
| 64 |
+
#### MultipleNegativesRankingLoss
|
| 65 |
+
```bibtex
|
| 66 |
+
@misc{henderson2017efficient,
|
| 67 |
+
title={Efficient Natural Language Response Suggestion for Smart Reply},
|
| 68 |
+
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
|
| 69 |
+
year={2017},
|
| 70 |
+
eprint={1705.00652},
|
| 71 |
+
archivePrefix={arXiv},
|
| 72 |
+
primaryClass={cs.CL}
|
| 73 |
+
}
|
| 74 |
+
```
|
| 75 |
+
|
| 76 |
+
<!--
|
| 77 |
+
## Glossary
|
| 78 |
+
|
| 79 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 80 |
+
-->
|
| 81 |
+
|
| 82 |
+
<!--
|
| 83 |
+
## Model Card Authors
|
| 84 |
+
|
| 85 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 86 |
+
-->
|
| 87 |
+
|
| 88 |
+
<!--
|
| 89 |
+
## Model Card Contact
|
| 90 |
+
|
| 91 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 92 |
+
-->
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.3.1",
|
| 4 |
+
"transformers": "4.48.0",
|
| 5 |
+
"pytorch": "2.5.1+cu124"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": "cosine"
|
| 10 |
+
}
|
modules.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "0_StaticEmbedding",
|
| 6 |
+
"type": "sentence_transformers.models.StaticEmbedding"
|
| 7 |
+
}
|
| 8 |
+
]
|