File size: 3,499 Bytes
ac82ad9 7da95e1 ac82ad9 6457cee ac82ad9 6457cee ac82ad9 6457cee ac82ad9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 |
{
"model_card": {
"Date & Time": "2024-12-05T09:20:42.556129",
"Model Card": [
"https://huggingface.co/FacebookAI/xlm-roberta-base"
],
"License Information": [
"mit"
],
"Citation Information": [
"\n@inproceedings{Wolf_Transformers_State-of-the-Art_Natural_2020,\n author = {Wolf, Thomas and Debut, Lysandre and Sanh, Victor and Chaumond, Julien",
"\n@Misc{peft,\n title = {PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods},\n author = {Sourab Mangrulkar and Sylvain Gugger and Lysandre Debut and Younes",
"@article{DBLP:journals/corr/abs-1911-02116,\n author = {Alexis Conneau and\n Kartikay Khandelwal and\n Naman Goyal and\n Vishrav Chaudhary and\n Guillaume Wenzek and\n Francisco Guzm{\\'{a}}n and\n Edouard Grave and\n Myle Ott and\n Luke Zettlemoyer and\n Veselin Stoyanov},\n title = {Unsupervised Cross-lingual Representation Learning at Scale},\n journal = {CoRR},\n volume = {abs/1911.02116},\n year = {2019},\n url = {http://arxiv.org/abs/1911.02116},\n eprinttype = {arXiv},\n eprint = {1911.02116},\n timestamp = {Mon, 11 Nov 2019 18:38:09 +0100},\n biburl = {https://dblp.org/rec/journals/corr/abs-1911-02116.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org}\n}",
"@inproceedings{reimers-2019-sentence-bert,\n title = \"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks\",\n author = \"Reimers, Nils and Gurevych, Iryna\",\n booktitle = \"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing\",\n month = \"11\",\n year = \"2019\",\n publisher = \"Association for Computational Linguistics\",\n url = \"https://arxiv.org/abs/1908.10084\",\n}"
]
},
"data_card": {
"Get SynthSTEL Training Triplets Dataset": {
"Date & Time": "2024-11-20T18:38:17.601393",
"Dataset Name": [
"StyleDistance/mstyledistance_training_triplets"
],
"Dataset Card": [
"https://huggingface.co/datasets/StyleDistance/mstyledistance_training_triplets"
]
},
"Get SynthSTEL Training Triplets Dataset (train split)": {
"Date & Time": "2024-11-20T18:57:23.493502"
},
"Get SynthSTEL Training Triplets Dataset (train split) (shuffle)": {
"Date & Time": "2024-11-30T22:23:37.582505"
}
},
"__version__": "0.35.0",
"datetime": "2024-11-30T22:23:38.698076",
"type": "TrainSentenceTransformer",
"name": "Train StyleDistance Model",
"version": 1.0,
"fingerprint": "d175c760f39a5f90",
"req_versions": {
"dill": "0.3.8",
"sqlitedict": "2.1.0",
"torch": "2.3.1",
"numpy": "1.26.4",
"transformers": "4.40.1",
"datasets": "2.17.0",
"huggingface_hub": "0.23.4",
"accelerate": "0.32.1",
"peft": "0.11.1",
"tiktoken": "0.7.0",
"tokenizers": "0.19.1",
"openai": "1.35.13",
"ctransformers": "0.2.27",
"optimum": "1.21.2",
"bitsandbytes": "0.43.1",
"litellm": "1.31.14",
"trl": "0.8.1",
"setfit": "1.0.3"
},
"interpreter": "3.10.9 (main, Apr 17 2023, 21:32:03) [GCC 7.5.0]"
} |