Build with Azure OpenAI, Copilot Studio & Agentic Frameworks — Microsoft Certified
Learn AI, Data Science & Business — Earn Certificates That Get You Hired
Overview
AI, Data Science & Cloud Certificates from Google, IBM & Meta — 40% Off
One plan covers every Professional Certificate on Coursera. 40% off Coursera Plus Annual.
Unlock All Certificates
Explore the implementation of Llama 2, the leading open-source Large Language Model, in LangChain for creating a conversational agent. Learn how to access and initialize the 70B parameter model fine-tuned for chat using Hugging Face transformers. Discover techniques for quantization, managing GPU memory requirements, and setting stopping criteria. Follow along as the video demonstrates loading Llama 2 into LangChain, creating a conversational agent, and applying prompt engineering. Gain insights into the future of open-source LLMs and their potential applications in artificial intelligence and natural language processing.
Syllabus
Llama 2 Model
Getting Access to Llama 2
Initializing Llama 2 70B with Hugging Face
Quantization and GPU Memory Requirements
Loading Llama 2
Stopping Criteria
Initializing Text Generation Pipeline
Loading Llama 2 in LangChain
Creating Llama 2 Conversational Agent
Prompt Engineering with Llama 2 Chat
Llama 2 Conversational Agent
Future of Open Source LLMs
Taught by
James Briggs