8 AI Model Architectures, Visually Explained!

must-know for AI engineers!

Get RAG-ready data from any unstructured doc!

Real-world documents are complex for LLMs to process directly.

Tensorlake transforms unstructured docs into LLM-ready data in just a few lines of code, as shown below:

• Supports images, documents, CSVs, slides, etc.

• Works on any complex layout, handwritten notes, multilingual data, etc.

• Returns document layout, structured extraction, page classification, and bounding boxes.

• And much more.

Here’s the GitHub repo → (don’t forget to star)

We’ll cover more in a hands-on demo soon.

---

8 AI model architectures, visually explained

Everyone talks about LLMs, but there’s a whole family of specialized models doing incredible things.

Here’s a quick breakdown:

• LLM (Large Language Models):

  • Text goes in, gets tokenized into embeddings, processed through transformers, and text comes out.

  • ChatGPT, Claude, Gemini, Llama.

• LCM (Large Concept Models)

  • Works at concept level, not tokens. Input is segmented into sentences, passed through SONAR embeddings, then uses diffusion before output.

  • Meta’s LCM is the pioneer.

• LAM (Large Action Models)

  • Turns intent into action. Input flows through perception, intent recognition, task breakdown, then action planning with memory before executing.

  • Rabbit R1, Microsoft UFO, Claude Computer Use.

• MoE (Mixture of Experts)

  • A router decides which specialized “experts” handle your query. Only relevant experts activate, results go through selection and processing.

  • Mixtral, GPT-4, DeepSeek.

• VLM (Vision-Language Models)

  • Images pass through a vision encoder, text through a text encoder. Both fuse in a multimodal processor, then a language model generates output.

  • GPT-4V, Gemini Pro Vision, LLaVA.

• SLM (Small Language Models)

  • LLMs optimized for edge devices. Compact tokenization, efficient transformers, and quantization for local deployment.

  • Phi-3, Gemma, Mistral 7B, Llama 3.2 1B.

• MLM (Masked Language Models)

  • Tokens get masked, converted to embeddings, then processed bidirectionally to predict hidden words.

  • BERT, RoBERTa, DeBERTa power search and sentiment analysis.

• SAM (Segment Anything Models)

  • Prompts and images go through separate encoders, feed into a mask decoder to produce pixel-perfect segmentation.

  • Meta’s SAM powers photo editing, medical imaging, and autonomous vehicles.

What else would you add?

Thanks for reading!

---

P.S. For those wanting to develop “Industry ML” expertise:

At the end of the day, all businesses care about impact. That’s it!

• Can you reduce costs?

• Drive revenue?

• Can you scale ML models?

• Predict trends before they happen?

We have discussed several other topics (with implementations) that align with such topics.

Here are some of them:

• Learn everything about MCPs in this ​crash course with 9 parts →​

• Learn how to build Agentic systems in a crash course with 14 parts.

• Learn how to build real-world RAG apps and evaluate and scale them in this crash course.

• Learn sophisticated graph architectures and how to train them on graph data.

• So many real-world NLP systems rely on pairwise context scoring. Learn scalable approaches here.

• Learn how to run large models on small devices using ​Quantization techniques.

• Learn how to generate prediction intervals or sets with strong statistical guarantees for increasing trust using ​Conformal Predictions.

• Learn how to identify causal relationships and answer business questions using causal inference in this crash course.

• Learn how to scale and implement ML model training in this practical guide.

• Learn techniques to reliably test new models in production.

• Learn how to build privacy-first ML systems using ​Federated Learning.

• Learn 6 techniques with implementation to compress ML models.

All these resources will help you cultivate key skills that businesses and companies care about the most.