Explore the capabilities of TinyLlama, a 1.1B Llama 2 model, in this 13-minute video tutorial. Discover the story behind TinyLlama's development, understand the concept of Chinchilla optimality, and learn about the training process. Follow along to run TinyLlama in Google Colab using the provided notebook link. Get hands-on experience with Jupyter Tiny Llama, including features like chatting with TinyLlama and other Llama models, saving and re-uploading chats. Access additional resources such as TinyLlama's GitHub repository, HuggingFace page, and live training link. Gain insights into the Chinchilla paper and find a Jupyter Lab installation guide. By the end of the video, grasp TinyLlama's capabilities and potential applications in natural language processing tasks.
TinyLlama: A 1.1B Llama 2 Model - Introduction and Practical Guide
Overview
Syllabus
TinyLlama: A 1.1B Llama 2 model
The story of TinyLlama
What is Chinchilla optimal?
Training TinyLlama
Run TinyLlama in Google Colab
Jupyter Tiny Llama
Recap of TinyLlama's capabilities
Taught by
Trelis Research
Related Courses
-
Connecting a Llama 2 Chatbot to the Internet - Search and Custom Functions
-
Fine-tuning Llama 2 for Tone or Style Using Shakespeare Dataset
-
LangChain MasterClass: Build 15 LLM Apps with Python
-
Llama 3 - 8B and 70B Models Deep Dive and Implementation Guide
-
Fine-tuning Llama 3.2 for Mental Health Sentiment Analysis Using TorchTune
-
Chat with Multiple PDFs Using Llama 2 and LangChain - Use Private LLM and Free Embeddings for QA
