Sanjitha Amarathungasanjithaamarathunga.hashnode.dev·Feb 24, 2024Is OpenAI's Sora Ready to Revolutionize Content Creation?In recent discussions, OpenAI's groundbreaking tool, Sora, has mixed both excitement and concern within the tech community over the world. Positioned as a challenging text-to-video model, Sora integrates deep learning, natural language processing, an...Discuss·1 likeAI
Yachay AIyachayai.hashnode.dev·Feb 22, 2024Uncertainty Estimation in TransformersIn our work on text-based geotagging, where many texts lack clear location references, having accurate uncertainty estimation is particularly valuable. In this blog post, we'll dive into different methods of achieving that. To make it easy to follow ...DiscussMachine Learning
Rishiraj AcharyaforBlogs by Team Callchimp.aicallchimp.hashnode.dev·Feb 19, 2024Foundations of Text Embeddings, Vector Databases, and RAGIf you're working with natural language processing (NLP) or even interested in it, you must have heard of text embeddings, vector databases, and retrieval augmented generation (RAG) which forms a symbiotic relationship that offers a sophisticated sol...Discuss·28 likes·55 readsMachine Learning
pramila jangidpramilajangid.hashnode.dev·Feb 8, 2024Code & No-code Mistral in WindowsHi there everyone, Hope coding is going awesome. In this blog, I am discussing how to run Mistral in your local Windows system. Before that let's understand - What is Mistral ? Why Mistral ? Different versions of models released by Mistral AI? Mistra...DiscussMistralAI
Trishanu DasforFutureSmart AI Blogblog.futuresmart.ai·Feb 5, 2024Exploring Data Science Horizons: A Novice's Adventure to Becoming a Data ExpertIntroduction: As a curious child, I was always fascinated by Maths and numbers. The spark ignited when I was first introduced to Calculus and Linear Algebra in high school. Upon entering college for my bachelor's degree, I explored different avenues ...Discuss·3 likes·391 readsinternships
Michael Mondoromikeymon.hashnode.dev·Jan 25, 2024Revisiting AI/ML with HuggingFace's Transformers ModuleArtificial Intelligence is the latest and greatest trend in tech. It stands to take away jobs, promote misinformation and is already invading the world of art, media and content creation. That being said, it is also pitched as the next step for human...Discuss·10 likesPython 3
Nishi Ajmeranishiajmera.com·Jan 23, 2024How do LLMs understand natural language?To answer this, we need to understand the Transformers architecture introduced by researchers at Google DeepMind in their paper "Attention is All You Need." But before we enter into Transformers Let's understand how natural language tasks were proces...DiscussDemystifying Large Language Models!llm
Yashkumar Dubeyblogwithdubey.hashnode.dev·Jan 22, 2024Let's Dive into Seq2Seq LearningIn the era of ever-growing landscape of Machine Learning Field, one paradigm stands out for its remarkable ability to adapt and applications that is Sequence-to-Sequence (Seq2Seq) Learning. It is all about training models to convert sequences from on...Discussencoders
Aakash Varmaaakashvarma.hashnode.dev·Jan 15, 2024Speculative SamplingThis article gives an overview of the DeepMind's paper Accelerating Large Language Model Decoding with Speculative Sampling Introduction In Transformer models, sampling is often constrained by memory bandwidth, resulting in the time to generate a tok...DiscussAI
Kaushal Powarwrittenbykaushal.hashnode.dev·Jan 10, 2024Phi-2 has an MIT license now! Why not perform RAG using it?Yesterday I read a few posts about Microsoft Phi-2 LLM's license changed to MIT. What so fuss around it though? The old license was like "You are allowed to conduct testing locally; however, for production purposes, it is essential to execute the app...Discuss·205 readsLLMphi2