Encoder Architechture - Transformer

-

 Transformer Architecture :



Transformer Architecture has 2 parts :

1. Encoder
2. Decoder

Each encoder and docoder part repeats 6 time. (mentioned in Attention is all you need paper)
They found that this is the best fit value from experiments.

Each encoder block is identical to others, same for decoder.

Now, lets zoom in to the Encoder Block.


6 Encoder Blocks:

Input would look like this:

  • Input : sentence
  • Output : positional Encoded Vector


Now, lets focus on Multihead attention and Normalization part:




Input : Output of first step (positional encoded vector)
Output :  Normalized vectors


Why is there residual connection and why do we need to add input and final vector after multihead attention?
  • Answer is not mentioned in Attention is all you need paper and nobody has an idea on the internet.
        People assume 2 possibilities:
  • 1. For stable training
  • 2. If the current layer messes up, we still have some good original data

Now, let's focus on Feed-Forward part:




Input : Output of previous layer (normalized vectors) 
Output : Introduced non-linearity and final normalized vectors





Steps:

1. 3 normalized vectors as input
2. stack them together and make a matrix. That will be 3*512
3. After that we have 2048 neurons, so matrix of 512*2048 
4. If we multiply above 2 matrix, we will have 3*2048 (So, we have increased the dimensions of the matrix.)
5. Now, this neurons will go to next layer and it will be 2048*512
6. multiply the matrix of layer 4 and 5. We will get 3* 512, which was the original size (Reduced dimensionality)
7. What is the need for increasing and reducing the dimensions?
  • We introduced non-linearity through ReLU
8.  Residual connection, sum, normalized vectors.


This is how one Encoder works, now this output will go the next block and process will repeat.

Why we need multiple encoder blocks?


- Natural Language is complex, and for model to understand it better, multiple blocks are used.

Example (for intuition):

  • First block: “Paris is the capital of France.”

    • Learns that “Paris” and “France” are related.

  • Second block: Uses the info to understand “capital” relates to “France” through “Paris.”

  • Third block: Sees the whole phrase and understands the full meaning in context.




Comments

Post a Comment

Popular posts from this blog

Extracting Tables and Text from Images Using Python

-
Image
In this blog, we'll explore a complete Python solution that detects and extracts tables and text from images using libraries like Transformers, OpenCV, PaddleOCR, and easyOCR. This step-by-step breakdown includes code to detect tables, extract content from individual table cells, and retrieve any remaining text in the image. Overview When working with scanned documents, such as invoices or forms, it is essential to accurately extract both structured information (like tables) and unstructured text. The approach we’ll explore uses Microsoft's pretrained object detection model to locate tables and OCR techniques to extract the text from both table cells and the rest of the image. Steps: 1. This code first detects table using microsoft's model. and save that image which contains detected table only  2. After that, from the detected table , we make a seperate image for each cell.  3. Then we read text from the image of each cell  4. Now, to read the extra texts except for the ...
Read more

Positional Encoding in Transformer

-
Image
1. Why Position Matters in Transformers? Transformers rely on self‑attention, which processes tokens in parallel. This means, unlike RNNs, they don’t inherently know the order of words. So, sentences like “Ravi killed the lion” vs. “The lion killed Ravi” would look identical to a vanilla Transformer—clearly problematic! 🧪 Idea #1: The Naïve Approach A simple fix would be to add index/position of the token in an embedding vector. Issues: Unbounded values: Position IDs can become huge (e.g. 100,000+ in long texts), destabilizing training. Discrete steps: Sharp jumps between integers disrupt gradient flow. 🧪 Idea #2: Normalize the Position Numbers What if we divide the position numbers by a constant to make them small and smooth? That helps a bit—values don’t explode anymore. Issues: Now, if you observe, in both the sentences, the word at second position has got the different values. 1 for sentence1, and 0.5 for sentence2. so, the Neural network will get confused while training, what a...
Read more

Chain Component in LangChain

-
Image
LangChain is a powerful framework for building applications with Large Language Models (LLMs). One of its core features is the Chain Component , which allows developers to link multiple operations together to create complex workflows. In this blog, we'll explore different types of chains in LangChain and demonstrate their usage with code examples. 1️⃣ LLMChain (Basic Single-Step Chain) 🔹 Executes a single LLM call based on a prompt. 🔹 The simplest chain type. ✅ Use Case: When you need a single prompt-response from an LLM. Example: 2️⃣ SequentialChain (Step-by-Step Execution) 🔹 Executes multiple chains in sequence where each step depends on the output of the previous step. ✅ Use Case: Multi-step processes where each step depends on the previous output . 📌  Example: Blog Outline → Content Expansion → Summary Example: 3️⃣ SimpleSequentialChain (Basic Sequential Execution) 🔹 Similar to SequentialChain, but only passes the last step’s output forward (less flexible). 🔹 ...
Read more