Latest Posts
-
·
12 RAG Pain Points and Solutions
Inspired by the paper “Seven Failure Points When Engineering a Retrieval Augmented Generation System” by Barnett et al., in this article, we will explore the seven pain points discussed in the paper and five additional common pain points in creating an RAG pipeline. Our focus is on understanding these pain points and their proposed solutions…
-
·
How do you incorporate domain knowledge and prior information into YOLO models?
Now that we’ve discussed different ways to incorporate domain knowledge and prior information into YOLO (You Only Look Once) models, let’s delve deeper into these techniques with some code snippets and practical examples. 1. Data Augmentation Data augmentation is a powerful technique to enrich the training dataset without collecting new data. It involves artificially creating…
-
·
How to Efficiently Tune Large Language Models with Early-Exiting
In the rapidly evolving world of deep learning, the efficiency of model training and inference has become as crucial as model accuracy itself. Large Language Models (LLMs) like GPT and BERT have pushed the boundaries of what’s possible in natural language processing, but their immense size and complexity present a significant challenge. The computational cost…
-
·
Running your own code copliot
In our latest episode in the #SimplifyingLLMs series! I’m here to guide you through the nuts and bolts of setting up and running a Code Copilot-like model on your personal computer. What is Ollama ? Ollama is a streamlined tool for running open-source LLMs locally, including Mistral and Llama 2. Ollama bundles model weights, configurations,…
-
·
Compressing Large Language Models: Introducing SliceGPT
In the evolving field of natural language processing, the efficiency and effectiveness of large language models (LLMs) are paramount. Among various model compression techniques, such as distillation, tensor decomposition, pruning, and quantization, we focus on an innovative approach called SliceGPT. This method demonstrates the capability to compress large models using a single GPU in just…
-
·
AI Native User Experience
The way we interact with technology is constantly evolving, and one of the most significant catalysts for this change is Artificial Intelligence (AI). AI is rapidly transforming user experiences (UX), creating more intuitive, personalized, and efficient interfaces. In this blog, we will explore the journey from the primitive use of AI in popular tools like…
-
·
Diffuse to Choose
The ever-growing demand for online shopping underscores the need for a more immersive shopping experience, allowing shoppers to virtually ‘try’ any product from any category (clothes, shoes, furniture, decoration, etc.) within their personal environments. The concept of a Virtual Try-All (Vit-All) model hinges on its functionality as an advanced semantic image composition tool. In practice,…
-
·
Launching Our First Pilot Course
We are thrilled to announce the launch of our first-ever pilot courses: “Maths for LLM/Deep-Learning” and “Practical NLP with Transformers” These courses represent a significant milestone in our journey to provide cutting-edge educational experiences in the field of artificial intelligence. Maths for LLM/Deep-Learning: Building the Foundation Our “Maths for LLM/Deep-Learning” course is designed to lay…
-
·
Recent Advances in Multi-Modal Large Language Models
In the past year, MultiModal Large Language Models (MM-LLMs) have undergone substantial advancements, augmenting off-the-shelf LLMs to support MM inputs or outputs via cost-effective training strategies. The resulting models not only preserve the inherent reasoning and decision-making capabilities of LLMs but also empower a diverse range of MM tasks. Model Architecture Modality Encoder The Modality…