thelatentlament.hashnode.devFine-Tuning BLIP-2 with LoRAIn my journey to dive deeper into multimodal AI systems, I decided to fine-tune BLIP-2, a powerful vision-language model trained on the Flickr8k dataset to generate image captions. What made this more exciting was integrating LoRA (Low-Rank Adaptatio...Feb 10·3 min read
thelatentlament.hashnode.devHow to run Mamba SSM on Kaggle?Recently Mamba has been making waves due to it’s linear time complexity in regards to processing tokens sequential. It is basically a Linear RNN under the hood but with selective forgetting and selective memorization, the very ablity that sets the Tr...Feb 3·5 min read
thelatentlament.hashnode.devFine-Tuning DeepSeek Math to Solve Emoji Equations: A Step-by-Step GuideThis blog post guides you through the process of fine-tuning the DeepSeek Math model to solve math problems expressed using emojis. This is a fun and engaging way to explore the capabilities of large language models (LLMs) and their ability to unders...Feb 2·9 min read
thelatentlament.hashnode.devBuilding a Transformer from Scratch: Translating Pseudo Code to C++In this blog post, I’ll walk you through my journey of building a transformer model from scratch and training it to translate pseudo-code into C++ code. This project combines natural language processing (NLP) with code generation, and I’m excited to ...Feb 1·11 min read
