This is the third in a series of videos where I will be testing various open-source models with my custom web search agent to see how well they perform. In this video, I benchmark Llama 3 70b (instruction tuned by TenyxChat), gpt-3.5 turbo, and phi-3 medium against Perplexity AI to see if my web search agent measures up.
Need to develop some AI? Let's chat: https://www.brainqub3.com/book-online
Register your interest in the AI Engineering Take-off course: https://www.data-centric-solutions.co...
Hands-on project (build a basic RAG app): https://www.educative.io/projects/bui...
Stay updated on AI, Data Science, and Large Language Models by following me on Medium: / johnadeojo
Build your own local “perplexity” with Ollama: • Build your own Local "Perplexity" with Oll...
How to setup with Llama 70b: • Build Open Source "Perplexity" agent with ...
GitHub repo: https://github.com/john-adeojo/custom...
Multi-Hop Questions: https://arxiv.org/pdf/2108.00573
Llama3-TenyxChat-70B model card: https://huggingface.co/tenyx/Llama3-T...
Chapters
Introduction: 00:00
Test Questions and approach: 01:25
Testing GPT 3.5-Turbo: 03:36
Results GPT 3.5-Turbo: 20:17
Testing Llama3-TenyxChat-70B: 21:45
Results Llama3-TenyxChat-70B: 42:10
Testing Phi 3 Medium Instruct: 44:40
Results Phi 3 Medium Instruct: 01:01:36