Finetuning Embedding Models using Sentence Transformers

Learn how you can easily fine-tune an embedding model like bert-base-uncased from scratch using sentence transformers using datasets like triplets or SNLI

Read the blog!

💡 Final Results

Here is the comparison between base model and fine-tuned model with SNLI dataset

Here is the comparison between base model and fine-tuned model with triplet dataset

🚀 Getting started

Prerequisites

• Python and anaconda installed on your machine
• A little bit knowledge about LLMs and embedding models

How to run?

• Clone the repository
• Open any jupyter notebook from repository and follow the instructions written in it
• Select your existing python environment or create one using anaconda
• Run the code