aws-samples/fine-tune-embedding-models-on-sagemaker
This repository contains samples for fine-tuning embedding models using Amazon SageMaker. Embedding models are useful for tasks such as semantic similarity, text clustering, and information retrieval. Fine-tuning these models on your specific domain data can greatly improve their performance.
This project helps data scientists and machine learning engineers improve how well a RAG system answers questions using your specific business data. It takes your unique pairs of questions and answers (or similar texts) and uses them to train an embedding model. The result is a more accurate RAG system that better understands your company's jargon and context, leading to more relevant responses.
No commits in the last 6 months.
Use this if you have a RAG system and want to significantly boost the accuracy and relevance of its answers by tailoring its understanding to your specific domain's text data.
Not ideal if you don't have existing pairs of similar texts (like question-answer pairs) for training, or if you are not working with a RAG system.
Stars
15
Forks
—
Language
Jupyter Notebook
License
MIT-0
Category
Last pushed
Feb 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/aws-samples/fine-tune-embedding-models-on-sagemaker"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ContextualAI/gritlm
Generative Representational Instruction Tuning
xlang-ai/instructor-embedding
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
liuqidong07/LLMEmb
[AAAI'25 Oral] The official implementation code of LLMEmb
hpcaitech/CachedEmbedding
A memory efficient DLRM training solution using ColossalAI
ritesh-modi/embedding-hallucinations
This repo shows how foundational model hallucinates and how we can fix such hallucinations using...