Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Embeddings (and how to create them) are, perhaps, the most interesting idea behind Large Language Models. I built a simple model to help you understand embeddings from scratch. Here is a step-by-step video explanation:

44,107 Aufrufe • vor 1 Jahr •via X (Twitter)

10 Kommentare

Profilbild von Santiago
Santiagovor 1 Jahr

Here is the same video, but now on YouTube: And here is the code I used in the video:

Profilbild von Matt Figdore
Matt Figdorevor 2 Jahren

This is the biggest productivity cheat code right now. Kiss reading documents goodbye. You can get an instant summary of any document with this tool.

Profilbild von Joao Marcos
Joao Marcosvor 1 Jahr

@PLynchado

Profilbild von Sumanth
Sumanthvor 1 Jahr

Impressive work Santiago. Thanks for the detailed tutorial!

Profilbild von Mohd Shadab Khan
Mohd Shadab Khanvor 1 Jahr

How do embeddings improve AI’s reasoning? Can this method work beyond text, like for images/videos?

Profilbild von Santiago
Santiagovor 1 Jahr

Yes, this works for images/videos. In fact, in this example, I create embeddings for images.

Profilbild von Foreign Policy Expert
Foreign Policy Expertvor 1 Jahr

Do embeddings matter as much anymore? We’ve got smolagents, better instruct models, and bigger contexts that allow for better hierarchical search and broader contextual understanding? Embedding search is cheaper, sure, but if the docs change over time don’t the embeddings “fail”

Profilbild von Ray | AI marketer - Social Media Assistant
Ray | AI marketer - Social Media Assistantvor 1 Jahr

How do you see embeddings improving the efficiency of your model? They can really help in capturing semantic relationships, which is crucial for better understanding context in AI.

Profilbild von Uncle Drei
Uncle Dreivor 1 Jahr

@memdotai meme this

Profilbild von scuzzlebot
scuzzlebotvor 1 Jahr

Great educational content on embeddings! These fundamental concepts are crucial for understanding how modern AI systems work. Looking forward to the video explanation.

Ähnliche Videos

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 Aufrufe • vor 2 Jahren