Microsoft's Phi 3.5 - The latest SLMs

In this video I look at yesterday's releases of Phi 3.5 models which include the mini, a new Mixture of Experts model as well as the new 3.5 Vision model.

For more tutorials on using LLMs and building Agents, check out my Patreon:

🕵️ Interested in building LLM Agents? Fill out the form below

👨‍💻Github:

⏱️Time Stamps:
00:00 Intro
00:10 Phi 3 GitHub
00:36 Phi 3.5 Mini Instruct
04:59 Phi 3.5 MoE Instruct
07:03 Phi 3.5 Vision Instruct
08:44 Phi 3 Cookbook
09:05 Code Demo

[thenoblerot]

Thanks Sam! You always have good content in a sea of clickbait nonsense :)

[thmo_]

the MoE wasn't wrong, the correct answer for that calculation was exactly 9.9996, rounding _is_ the next step. So I'd say it did better at that specific question..

[supercurioTube]

Thanks for the coverage, I'd be interested in a tool use / RAG and other utilities comparison with Llama 3.1 8B quantized aggressively to bridge the gap in RAM and performance!

[blossom_rx]

Unfortunately every Phi model I tested so far had a model collapse after 3 to 5 queries. I have this only with Microsoft models OR models I truncated on my own. I do not understand the hype and do not trust the benchmarks. Just to make clear: I have about 15 different official models running locally that were not tampered with and NONE except the Microsoft models have this issue.

[jeremybristol]

Surprisingly good. Better than v3. But still get's stuck in loops as the response context length grows. Experimenting with prompts to avoid this.

[yotubecreators]

just wanted to like this video for the 2nd time lol already found myself liked it 2 weeks ago

[라면먹고싶다-dw]

What are some different use cases for Mini and MoE? For example if you want to do a RAG application, which would be more suitable?

[Diego_UG]

Is there any cheap way to finetune these small models with proprietary data?

[etherhealingvibes]

Phi 3.5 is mindblowing. Works crazy fast and accurate for function calling, and json answers also.

[WillJohnston-wgew]

Does anyone know of a source for community/conversation on LLMs and business? I'm a technologist developing an app and would really like to find a good source for discussing ideas and what's working/not working.

[xthesayuri]

It's funny. Every time a new Phi model comes out I get so insanely bearish for LLMs because they always suck. Just gaming the benchmark but are horrendous to use.

[IdPreferNot]

How much longer are we going to pretend that these are in any way practical? No on prem running for anyone except large corp and many of the privacy issues open source was supposed to address arise come back once you start using someone else's hardware. Guess Its great to see smaller models improve and push foundation models, but if you want to do stuff with any off these, especially with agentic processes gobbling thousands of tokens, latency and performance demand hosted service.... might as well go free flash, mini with no setup or hosting issues.