| { | |
| "model_card": { | |
| "Date & Time": "2024-01-18T18:59:52.071528", | |
| "Model Card": [ | |
| "https://huggingface.co/google/t5-v1_1-base" | |
| ], | |
| "License Information": [ | |
| "apache-2.0" | |
| ], | |
| "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" | |
| ] | |
| }, | |
| "data_card": { | |
| "Generate Research Paper Abstracts": { | |
| "Date & Time": "2024-01-18T18:59:52.071528", | |
| "Model Name": [ | |
| "gpt-4" | |
| ], | |
| "Model Card": [ | |
| "https://cdn.openai.com/papers/gpt-4-system-card.pdf" | |
| ], | |
| "License Information": [ | |
| "https://openai.com/policies" | |
| ], | |
| "Citation Information": [ | |
| "@article{OpenAI2023GPT4TR,\n title={GPT-4 Technical Report},\n author={OpenAI},\n journal={ArXiv},\n year={2023},\n volume={abs/2303.08774},\n url={https://api.semanticscholar.org/CorpusID:257532815}\n}", | |
| "@article{ouyang2022training,\n title={Training language models to follow instructions with human feedback},\n author={Ouyang, Long and Wu, Jeffrey and Jiang, Xu and Almeida, Diogo and Wainwright, Carroll and Mishkin, Pamela and Zhang, Chong and Agarwal, Sandhini and Slama, Katarina and Ray, Alex and others},\n journal={Advances in Neural Information Processing Systems},\n volume={35},\n pages={27730--27744},\n year={2022}\n}" | |
| ] | |
| }, | |
| "Generate Tweets from Abstracts": { | |
| "Date & Time": "2024-01-18T18:59:52.071528", | |
| "Model Name": [ | |
| "gpt-4" | |
| ], | |
| "Model Card": [ | |
| "https://cdn.openai.com/papers/gpt-4-system-card.pdf" | |
| ], | |
| "License Information": [ | |
| "https://openai.com/policies" | |
| ], | |
| "Citation Information": [ | |
| "@article{OpenAI2023GPT4TR,\n title={GPT-4 Technical Report},\n author={OpenAI},\n journal={ArXiv},\n year={2023},\n volume={abs/2303.08774},\n url={https://api.semanticscholar.org/CorpusID:257532815}\n}", | |
| "@article{ouyang2022training,\n title={Training language models to follow instructions with human feedback},\n author={Ouyang, Long and Wu, Jeffrey and Jiang, Xu and Almeida, Diogo and Wainwright, Carroll and Mishkin, Pamela and Zhang, Chong and Agarwal, Sandhini and Slama, Katarina and Ray, Alex and others},\n journal={Advances in Neural Information Processing Systems},\n volume={35},\n pages={27730--27744},\n year={2022}\n}" | |
| ] | |
| } | |
| }, | |
| "__version__": "0.1.0", | |
| "datetime": "2024-01-18T18:59:52.071528", | |
| "type": "TrainHFFineTune", | |
| "name": "Train an Abstract => Tweet Model", | |
| "version": 1.0, | |
| "fingerprint": "3e30bb93dbb5e421", | |
| "req_versions": { | |
| "dill": "0.3.7", | |
| "sqlitedict": "2.1.0", | |
| "torch": "2.1.2", | |
| "numpy": "1.26.3", | |
| "transformers": "4.36.2", | |
| "datasets": "2.16.1", | |
| "huggingface_hub": "0.20.2", | |
| "accelerate": "0.26.1", | |
| "peft": "0.7.1", | |
| "tiktoken": "0.5.2", | |
| "tokenizers": "0.15.0", | |
| "openai": "1.8.0", | |
| "ctransformers": "0.2.27", | |
| "optimum": "1.16.1", | |
| "bitsandbytes": "0.42.0", | |
| "litellm": "1.15.3", | |
| "trl": "0.7.6", | |
| "setfit": "1.0.3" | |
| }, | |
| "interpreter": "3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0]" | |
| } |