• Preference Training for LLMs in a Nutshell

    Large Language Models (LLMs) harness the power of unsupervised learning(self-supervised to be precise) on extensive datasets, showcasing remarkable natural language processing capabilities. However, these models exhibit inherent limitations when not trained using Reinforcement Learning with Human Feedback (RLHF). One significant drawback lies in their lack of specificity and control. Although...

  • Efficient Book Summarization using Large Language Models

    In the realm of summarizing entire books using Large Language Models (LLMs), the challenge of context length emerges as a prominent hurdle. These models, while powerful, are constrained by their capacity to handle only a certain amount of text at a time. Given the extensive nature of books, accommodating the...

  • Building your own Llama(🦙)Chat

    Ever wanted to create your very own chatbot, just like the ones you talk to on the internet? Well, you’re in for a treat! In this blog, I’ll guide you through the process using Llama-2 LLM. But wait, there’s more. I’ll also help you design a cool and easy-to-use chatbot...

  • Extrapolating to longer sequence lengths using ALiBi

    One of the core components of transformer models is the attention mechanism, which allows the model to focus on specific parts of the input sequence while processing it. Traditionally, attention mechanisms have relied on positional encodings to provide information about the order of tokens in a sequence. However, a newer...

  • The Power of Prompting - A Journey from Simple Prompts to Tree of Thought Strategies

    In the ever-evolving landscape of natural language processing, language models (LMs) have emerged as incredibly versatile tools. These models, such as GPT-4, have demonstrated their prowess in various tasks, from generating coherent text to solving intricate problems. Yet, the key to unlocking their true potential lies in how we prompt...

  • Working with Generative Language Models

    This extensive article will discuss the current trending technology in the Machine Learning space, namely ChatGPT and other Large Language Models (LLMs). With the introduction of ChatGPT by OpenAI, an LLM that is being touted as the initial step towards Artificial General Intelligence, the tech industry is in a state...

  • Decide better, Subconsciously

    Table of Contents Introduction The Three Pillars of Mind Ability of Subconsciousness The Hypothetical Analogy Deciding Better Introduction We always have a desire for the things to happen in the manner we want them to be – be it rational or irrational, ethical or non ethical. Ever wondered about the...

  • Courses You Should Take

    CS230 MIT Deep Learning Course 2019 DeepMind’s Advanced Deep Learning and Reinforcement Learning Nvidia’s Webinars on Deep Learning Frameworks Deep Learning at Oxford