👉 Get all of our make.com templates here (including these ones): https://www.theaiautomators.com/?utm_source=youtube&utm_medium=video&utm_campaign=tutorial&utm_content=llama_auto
Book a 60-minute call with us: https://www.theaiautomators.com/book-a-call/
In this video I put the new Meta Llama 3.1 models to the test by having them power 10 AI Automations. I then compare the 405B, 70B and 8B models results side-by-side.
Get Make: https://www.make.com/en/register?pc=aiauto
Meta Llama 3.1 – https://llama.meta.com/
Fireworks – https://fireworks.ai/
Firecrawl URL – https://www.firecrawl.dev/
Supabase URL – https://supabase.com/
0:00 – Overview of Lama 3.1 models
0:14 – Test scenarios overview
0:47 – API options and costs
1:17 – Llama model pricing comparison
2:01 – Fireworks AI
2:21 – PowerPoint generation
5:32 – Web scraping
9:39 – Large documents
12:42 – Blog article generation
15:36 – Database reports
18:43 – Sentiment analysis
22:15 – Text summarization
24:12 – System message test
24:56 – Prompt injection test
25:31 – Verdict
Tested on Make.com, the automations include generating Python code and a Powerpoint Presentation, generating SQL queries, structured data extraction, text generation, text summarization, text classification, sentiment analysis while also testing for prompt injections.
source
date: 2024-07-26 13:29:28
duration: 00:27:06
author: UCwvXnrOCRlhokHlJwohf2OA
