GitHub - AreebAhmad-02/Embedding-Models-Finetuning: The repository includes code for generating synthetic datasets using Zypher 7B from Hugging Face, with QA embeddings and anchor-positive similarity scores. It also handles preprocessing of scanned PDFs with OCR via Google Vision API. The code supports model fine-tuning with various loss functions and evaluation using Sentence Transformers evaluator

Name		Name	Last commit message	Last commit date
Latest commit History 30 Commits
data after preprocessing		data after preprocessing
data		data
synthetic data		synthetic data
Another_copy_of_Fine_tuning_Embedding_Models.ipynb		Another_copy_of_Fine_tuning_Embedding_Models.ipynb
Fine_tuning_Embedding_Models.ipynb		Fine_tuning_Embedding_Models.ipynb
OCR_of_Scanned_PDF_Using_Google_VIsion_API_and_Preprocessing.ipynb		OCR_of_Scanned_PDF_Using_Google_VIsion_API_and_Preprocessing.ipynb
README.md		README.md

Provide feedback