Summarizing OpenAI ’s GPT-2 and GPT-3 models — In one of the last article, I discussed about Decoder-only transformer model, which is GPT-1 model from OpenAI. Decoder-only Transformer model Understanding Large Language models with GPT-1medium.com GPT-2 model is designed by making minor changes in the architecture of GPT-1 model. Similarly, GPT-3 model is slightly an enhanced version of GPT-2 model.

A conceptual understanding of Zero shot learning — Zero-Shot Learning is a subfield of transfer learning, a machine learning method where a model developed for a one task is reused as the starting point for a model on a different task. On a broader level, there are two types of transfer learning: homogenous transfer learning — where the…

A detailed view on positional and keyword arguments — To understand about *args and **kwargs, you should have an idea about Pass by reference, positional arguments, keyword arguments, packed values and unpacked values. These are the articles, which are recommended to read before following through this article. Parameter vs Arguments and Pass by reference Understanding of Pass by reference with module scope and function scopepub.aimind.so

Understanding of Pass by reference with module scope and function scope — Function is a sequence of program instructions that performs a specific task, packaged as a unit — wikipedia A function is a block of code that performs specific task. It can be reused multiple times. When a function call is made, the program will pause the current program and execute…

A detailed explanation on positional arguments and keyword arguments in python — Positional arguments The most common way of assigning arguments to parameters is through the order in which they are passed in (that is through their position). A function example_func() is defined with two parameters x and y def example_func(x, y): # body of the function return None When this function call is…

Exploring Large Language models with underlying concepts — Bi-directional Encoder Representation from Transformers — is proposed by Google in the research paper — BERT-Pre-training of Deep Bidirectional Transformers for Language Understanding, which became revolutionary in the field of NLP (Natural Language Processing). The biggest challenge in NLP-based tasks is the lack of enough training data. Even though there…

Understanding Large Language models with GPT-1 — Over past 6 months, everywhere around the internet — ChatGPT was the term buzzing around and it is in fact acknowledged that the next-decade will be the decade of generative models. There are many Generative models like Autoregressive models, Variational autoencoders, Normalizing flow models, Generative adversarial networks, etc.. ChatGPT could…

Understanding Transformer model — Self-Attention is at the core of Transformer model and in fact, the entire LLM models mechanisms relies on the Transformer model. This is one of the trickiest model, I studied till date. Transformer model is an advanced sequence to sequence model, which consists of group of Encoder-Decoder models BUT, the…

Sequence-Sequence model with Attention mechanism — There are Encoder-Decoder — seq2seq models which are capable in solving many problems like Machine Translation, Image captioning and many more. Then, Why do we need enhanced sequence-to-sequence models like Attention model? At least once, everyone of you might have experienced Translation speech either in political meetings or in movies…