У нас вы можете посмотреть бесплатно Lecture 1 - Reasoning LLMs from Scratch - Series Introduction или скачать в максимальном доступном качестве, видео которое было загружено на ютуб. Для загрузки выберите вариант из формы ниже:
Если кнопки скачивания не
загрузились
НАЖМИТЕ ЗДЕСЬ или обновите страницу
Если возникают проблемы со скачиванием видео, пожалуйста напишите в поддержку по адресу внизу
страницы.
Спасибо за использование сервиса ClipSaver.ru
This year has arguably been the year where we are seeing more and more of “reasoning models”, for which the main catalyst was Deep-Seek R1. Every day, I read dozens of articles on LinkedIn about integration of reasoning models by companies for a more trustworthy customer experience, or a comparison of reasoning models offered by LLM providers. The most recent article I came across was that of Fractal Analytics coming up with India’s first Large Reasoning Model (LRM). Despite the growing interest in understanding how reasoning models work and function, I could not find a single course/resource which explained everything about reasoning models from scratch. All I could see was flashy 10-20 minute videos such as “o1 model explained” or one-page blog articles. This was a problem. If our mission is to make AI accessible to all, we should also make reasoning LLMs accessible to all. The thought of curating a course for this started to take shape in my mind around 2 months back. Today, I am proud to announce that, after countless hours spent in reading and researching, we are launching a course on “Reasoning LLMs from Scratch” on our YouTube channel. This course will focus heavily on the fundamentals and give you the confidence to understand and also build a reasoning model from scratch. There will be a total of 4 modules with 40+ hours of content. The 4 methods we will discuss in detail are: (1) Inference-Time Compute Scaling (2) Pure Reinforcement Learning (Includes a hands-on tutorial to build a pure RL based reasoning model) (3) Supervised Fine-Tuning and Reinforcement Learning (4) Pure Supervised Fine-Tuning and Distillation (Includes a hands-on tutorial to build a reasoning model using distillation) Hope all of you enjoy the lecture!