shobrook/weightgain
Train an adapter for any embedding model in under a minute
This tool helps developers improve the accuracy of their Retrieval Augmented Generation (RAG) systems by fine-tuning embedding models for specific use cases. It takes an existing embedding model and a dataset of query-chunk pairs (which can be synthetically generated), then outputs a custom 'adapter' that transforms embeddings for better relevance. This is ideal for machine learning engineers and data scientists building RAG applications.
129 stars. No commits in the last 6 months.
Use this if you need to optimize the performance of your RAG system's information retrieval, ensuring that searches return more relevant results from your specific knowledge base.
Not ideal if you are not working with embedding models or RAG systems, or if you need to train an embedding model from scratch rather than adapt an existing one.
Stars
129
Forks
7
Language
Python
License
MIT
Category
Last pushed
Apr 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/shobrook/weightgain"
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...