Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/adrianmarino/t5-fine-tunning
T5 fine tunning for sentiment analysis
https://github.com/adrianmarino/t5-fine-tunning
llm python pytorch-lightning sentiment-classification t5-model
Last synced: 1 day ago
JSON representation
T5 fine tunning for sentiment analysis
- Host: GitHub
- URL: https://github.com/adrianmarino/t5-fine-tunning
- Owner: adrianmarino
- Created: 2023-11-15T13:38:35.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2023-11-18T12:54:35.000Z (about 1 year ago)
- Last Synced: 2023-11-18T13:40:22.936Z (about 1 year ago)
- Topics: llm, python, pytorch-lightning, sentiment-classification, t5-model
- Language: Jupyter Notebook
- Homepage:
- Size: 36.1 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# t5-fine-tunning
T5 fine-tuning for sentiment analysis. It is very simple to adapt this model to other tasks such as recommendations, summaries, etc. See the paper for more details: [Exploring the Limits of Transfer Learning with a Unified
Text-to-Text Transformer](https://arxiv.org/pdf/1910.10683.pdf)**Notebooks**
* [Sentiment_analisys: Prepare_dataset](https://github.com/adrianmarino/t5-fine-tunning/blob/master/notebooks/sentiment_analisys/1_prepare_dataset.ipynb)
* [Sentiment_analisys: Training an evaluation](https://github.com/adrianmarino/t5-fine-tunning/blob/master/notebooks/sentiment_analisys/2_sentiment_analisys.ipynb)
* [Recommender](https://github.com/adrianmarino/t5-fine-tunning/blob/master/notebooks/T5_recommender.ipynb)## Referencies
* [Huggingface T5 documentation](https://huggingface.co/docs/transformers/v4.35.1/en/model_doc/t5#t5)
* [T5 Fine tunning](https://colab.research.google.com/github/patil-suraj/exploring-T5/blob/master/t5_fine_tuning.ipynb#scrollTo=SDVQ04fGRb1v)
* [Exploring the Limits of Transfer Learning with a UnifiedText-to-Text Transformer](https://arxiv.org/pdf/1910.10683.pdf)