Hugging Face

AI Large Language Models

How to Run 70Bn Llama 3 Inference on a Single 4GB GPU

This video is from Rohan-Paul-AI. Code : Airllm Github –

Read More
AI Generative AI Large Language Models

Prompt Engineering: How to Trick AI into Solving Your Problems

This video is from Shaw Talebi. This is the 4th video in a series on using large language models (LLMs) in practice. Here, I review Prompt Engineering, 7 prompting tricks, and walk through example code that uses LangChain to build an AI application.

Read More
AI AWS Generative AI

How to Get Started With Generative AI Using Amazon SageMaker

Generative AI enables organizations to innovate faster as well as reinvent customer experiences and applications. In this session, we’ll discuss best practices to deploy open source large language models (LLMs) using Amazon SageMaker. We’ll also show you how easy it is to access TII’s Falcon 40B, the #1 LLM on the Hugging Face Open LLM […]

Read More
AWS Machine Learning

Unlock the Power of GenAI Experiences with AWS ML Heroes in 15 Minutes

This video is from AWS Online Tech Talks. Tune in to learn how to build AI-powered experiences leveraging the latest technology in Machine Learning and Generative AI with Hugging Face and Amazon SageMaker. In part one of this two part series, we will walk through building a generative AI application through Amazon SageMaker’s fully managed […]

Read More
Generative AI

Is Generative AI Is About To Reset Everything?

Forbes explains that generative AI like ChatGPT and Stable Diffusion are about to change not only how you work, but how the content you consume is produced. Forbes spoke with a number of leading voices in the AI space to determine both the benefits and the dangers of this next wave of technological innovation, and find […]

Read More

Delta Live Tables with Auto Loader and Hugging Face Sentiment Analysis

Modern data engineering requires more advanced data lifecycle for data ingestion, transformation, and processing. In this session, learn how the Databricks Lakehouse Platform provides an end-to-end data engineering solution — ingestion, processing and scheduling — that automates the complexity of building and maintaining pipelines and running ETL workloads directly on a data lake, so your […]

Read More