If you found it insightful, reshare it with your network.Find me → @_avichawlaEvery day, I share tutorials and insights on DS, ML, LLMs, and RAGs.Avi Chawla (@_avichawla):100%That's how much data you re-index when you change embedding models.And most teams treat that as unavoidable.Imagine you built a RAG pipeline using an embedding model with high retrieval quality, and it ships to production.Six months later, a better embedding model is https://t.co/NIgrqffgyo ...

Download Voyage-4-nano from HF: https://t.co/mXjgxriy6d ...

100%That's how much data you re-index when you change embedding models.And most teams treat that as unavoidable.Imagine you built a RAG pipeline using an embedding model with high retrieval quality, and it ships to production.Six months later, a better embedding model is released that delivers similar quality at a lower cost.But your existing embeddings live in one vector space, while the new model produces embeddings in a different one, which makes them incompatible.Switching models now means rebuilding th ...

RT Avi Chawla (@_avichawla)Researchers built a new RAG approach that:- does not need a vector DB.- does not embed data.- involves no chunking.- performs no similarity search.And it hit 98.7% accuracy on a financial benchmark (SOTA).Here's the core problem with RAG that this new approach solves:Traditional RAG chunks documents, embeds them into vectors, and retrieves based on semantic similarity.But similarity ≠ relevance.When you ask "What were the debt trends in 2023?", a vector search returns chunks that ...

The efficacy of mixed precision scaling over traditional training is evident from the image below.Mixed precision training is over 2.5x faster than conventional training in a mini neural network.Typical speeds are 4-6x in bigger neural networks.Check this 👇 https://t.co/RRGQZ3bYLI ...

A simple technique trains neural nets 4-6x faster!- OpenAI used it in GPT models.- Meta used it in LLaMA models.- Google used it in Gemini models.Here's a breakdown (with code): ...

RT Avi Chawla (@_avichawla)https://t.co/kzyjbAxoUq ...

https://t.co/kzyjbAxoUq ...

If you found it insightful, reshare it with your network.Find me → @_avichawlaEvery day, I share tutorials and insights on DS, ML, LLMs, and RAGs. https://t.co/AlW9UxvMCDAvi Chawla (@_avichawla):You're in a Research Scientist interview at Google.Interviewer: We have a base LLM that's terrible at maths. How would you turn it into a maths & reasoning powerhouse?You: I'll get some problems labeled and fine-tune the model.Interview over.Here's what you missed: ...

Before I conclude, let me address an important question:When should you use reinforcement fine-tuning (RFT) versus supervised fine-tuning (SFT)?I created this diagram to provide an answer: https://t.co/bo2W4NXk3a ...