Uploaded April 2025 | Updated November 2026, 2 days ago
Meta's Llama 4 is a family (herd) of multimodal models - from 109B (Scout) to 2T (Behemoth) parameters with mixture of experts (MoE) architecture. Llama 4 Scout supports 10M context window! Benchmarks say the models are amazing - but are they? Let's try it out!
Llama 4 blogpost: ai.meta.com/blog/llama-4-multimodal-intelligence
Llama 4 on HuggingFace: huggingface.co/blog/llama4-release
AI Bootcamp: mlexpert.io
LinkedIn: linkedin.com/in/venelin-valkov
Follow me on X: twitter.com/venelin_valkov
Discord: discord.gg/UaNPxVD6tv
Subscribe: bit.ly/venelin-subscribe
GitHub repository: github.com/curiousily/AI-Bootcamp
👍 Don't Forget to Like, Comment, and Subscribe for More Tutorials!
00:00 - Welcome
00:18 - Llama 4
05:23 - Benchmarks
06:39 - Notebook setup
08:08 - Hip Hop lyrics
09:31 - Coding
11:15 - Data labeling
13:13 - Text summarization
14:44 - LinkedIn post
15:44 - Structured data extraction (with vision test)
18:31 - RAG/Question-answering
19:41 - Table data extraction
20:45 - Conclusion
Join this channel to get access to the perks and support my work:
youtube.com/channel/UCoW_WzQNJVAjxo4osNAxd_g/join
#llama #artificialintelligence #chatbot #chatgpt #python
Meta's Llama 4 is a family (herd) of multimodal models - from 109B (Scout) to 2T (Behemoth) parameters with mixture of experts (MoE) architecture. Llama 4 Scout supports 10M context window! Benchmarks say the models are amazing - but are they? Let's try it out!
Llama 4 blogpost: ai.meta.com/blog/llama-4-multimodal-intelligence
Llama 4 on HuggingFace: huggingface.co/blog/llama4-release
AI Bootcamp: mlexpert.io
LinkedIn: linkedin.com/in/venelin-valkov
Follow me on X: twitter.com/venelin_valkov
Discord: discord.gg/UaNPxVD6tv
Subscribe: bit.ly/venelin-subscribe
GitHub repository: github.com/curiousily/AI-Bootcamp
👍 Don't Forget to Like, Comment, and Subscribe for More Tutorials!
00:00 - Welcome
00:18 - Llama 4
05:23 - Benchmarks
06:39 - Notebook setup
08:08 - Hip Hop lyrics
09:31 - Coding
11:15 - Data labeling
13:13 - Text summarization
14:44 - LinkedIn post
15:44 - Structured data extraction (with vision test)
18:31 - RAG/Question-answering
19:41 - Table data extraction
20:45 - Conclusion
Join this channel to get access to the perks and support my work:
youtube.com/channel/UCoW_WzQNJVAjxo4osNAxd_g/join
#llama #artificialintelligence #chatbot #chatgpt #python










