aws-samples/finetune-bge-embeddings-blog
Code associated with the blog post titled, "Fine-Tuning BGE Embeddings Using Synthetic Data from Amazon Bedrock"
This project helps machine learning engineers and data scientists enhance the accuracy of information retrieval and semantic search. It takes your existing text data and uses Amazon Bedrock to generate diverse synthetic training examples. The output is a fine-tuned BGE embedding model, deployed via Amazon SageMaker, that better understands your specific domain's terminology and relationships.
No commits in the last 6 months.
Use this if you need to improve the relevance and precision of search results or recommendation systems within a specific subject area, especially when you have limited labeled data for training.
Not ideal if you don't have an AWS account, are unfamiliar with SageMaker Studio, or are looking for a pre-trained model without customization.
Stars
11
Forks
1
Language
Jupyter Notebook
License
MIT-0
Category
Last pushed
Sep 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/aws-samples/finetune-bge-embeddings-blog"
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...