| { | |
| "model_card": { | |
| "Date & Time": "2024-08-05T13:02:15.447523", | |
| "Model Card": [ | |
| "https://huggingface.co/FacebookAI/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-1907-11692,\n author = {Yinhan Liu and\n Myle Ott and\n Naman Goyal and\n Jingfei Du and\n Mandar Joshi and\n Danqi Chen and\n Omer Levy and\n Mike Lewis and\n Luke Zettlemoyer and\n Veselin Stoyanov},\n title = {RoBERTa: {A} Robustly Optimized {BERT} Pretraining Approach},\n journal = {CoRR},\n volume = {abs/1907.11692},\n year = {2019},\n url = {http://arxiv.org/abs/1907.11692},\n archivePrefix = {arXiv},\n eprint = {1907.11692},\n timestamp = {Thu, 01 Aug 2019 08:59:33 +0200},\n biburl = {https://dblp.org/rec/journals/corr/abs-1907-11692.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": "2024-07-22T12:32:49.982528", | |
| "Dataset Name": [ | |
| "SynthSTEL/styledistance_training_triplets" | |
| ], | |
| "Dataset Card": [ | |
| "https://huggingface.co/datasets/SynthSTEL/styledistance_training_triplets" | |
| ] | |
| }, | |
| "Get SynthSTEL Training Triplets Dataset (train split)": { | |
| "Date & Time": "2024-07-22T12:34:32.628286" | |
| }, | |
| "Get SynthSTEL Training Triplets Dataset (train split) (shuffle)": { | |
| "Date & Time": "2024-07-22T12:40:47.902534" | |
| }, | |
| "Get SynthSTEL Training Triplets Dataset (train split) (shuffle) (take)": { | |
| "Date & Time": "2024-07-22T12:40:53.004017" | |
| }, | |
| "Get SynthSTEL Training Triplets Dataset (train split) (shuffle) (take) (select_columns)": { | |
| "Date & Time": "2024-07-22T12:40:54.367439" | |
| }, | |
| "concat(Get SynthSTEL Training Triplets Dataset (train split) (shuffle) (take) (select_columns), Get SynthSTEL Training Triplets Dataset #2 (take))": { | |
| "Date & Time": "2024-07-22T12:43:44.056927" | |
| }, | |
| "concat(Get SynthSTEL Training Triplets Dataset (train split) (shuffle) (take) (select_columns), Get SynthSTEL Training Triplets Dataset #2 (take)) (shuffle)": { | |
| "Date & Time": "2024-07-23T14:22:55.032374" | |
| } | |
| }, | |
| "__version__": "0.35.0", | |
| "datetime": "2024-07-23T14:22:55.632236", | |
| "type": "TrainSentenceTransformer", | |
| "name": "Train Wegmann + StyleDistance Model", | |
| "version": 1.0, | |
| "fingerprint": "620cd4c756865563", | |
| "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]" | |
| } |