Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning

techcommunity.microsoft.com

Post reply on HN
Print view View original

121–130 of 148 posts

Re: Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning

#121

Post by criddell »

chairhairair wrote: post #119
criddell wrote: post #110

Earlier quoted context omitted.

If you graded humanity on their reasoning ability, I wonder where these models would score? I think once they get to about the 85th percentile, we could upgrade the phrase to advanced reasoning. I'm roughly equating it with the percentage of the US population with at least a master's degree.

All current LLMs openly make simple mistakes that are completely incompatible with true "reasoning" (in the sense any human would have used that term years ago). I feel like I'm taking crazy pills sometimes.

How do you assess how true one's reasoning is?

Re: Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning

#122

Post by ben_w »

dartos wrote: post #116
ben_w wrote: post #115

Earlier quoted context omitted.

SVGs themselves are just an image format; but because of their vector nature, they could easily be mapped onto values from a simulation in a physics engine — at least, in the game physics sense of the word, rods and springs etc., as a fluid simulation is clearly a better map to raster formats. If that physics engine were itself a good model for the real world, then you could do simulated evolution to get an end resul…

> but because of their vector nature, they could easily be mapped onto values from a simulation in a physics engine. I don’t think the fact that the images are described with vectors magically makes it better for representing physics than any other image representation. Maybe less so, since there will be so much textual information not related to the physical properties of the object. What about them makes it easier…

For rendering them, more than for anything else. There's a convenient 1-to-1 mapping in both directions.

You can of course just rasterise the vector for output, it's not like people view these things on oscilloscopes.

Re: Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning

#123

Post by bloomingkales »

alganet wrote: post #109
kgwgk wrote: post #105

Earlier quoted context omitted.

> you'll have at least double the performance of a base m4 mini For $500 all included?

The base mini is 599. Here's a config for around the same price. All brand new parts for 573. You can spend the difference improving any part you wish, or maybe get an used 3060 and go AM5 instead (Ryzen 8400F). Both paths are upgradeable. https://pcpartpicker.com/list/ftK8rM Double the LLM performance. Half the desktop performance. But you can use both at the same time. Your computer will not slow down when running…

That’s a really nice build.

Re: Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning

#124

Post by regularfry »

refulgentis wrote: post #21
syntaxing wrote: post #16

Earlier quoted context omitted.

Wow, those responses are better than I expected. Part of me was expecting terrible responses since Phi-3 was amazing on paper too but terrible in practice.

One of the funniest tech subplots in recent memory. TL;DR it was nigh-impossible to get it to emit the proper "end of message" token. (IMHO the chat training was too rushed). So all the local LLM apps tried silently hacking around it. The funny thing to me was no one would say it out loud. Field isn't very consumer friendly, yet.

In a field like this the self-doubt of "surely it wouldn't be this broken, I must just be holding it wrong" is strong.

Re: Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning

#125

Post by alganet »

bloomingkales wrote: post #123
alganet wrote: post #109

Earlier quoted context omitted.

The base mini is 599. Here's a config for around the same price. All brand new parts for 573. You can spend the difference improving any part you wish, or maybe get an used 3060 and go AM5 instead (Ryzen 8400F). Both paths are upgradeable. https://pcpartpicker.com/list/ftK8rM Double the LLM performance. Half the desktop performance. But you can use both at the same time. Your computer will not slow down when running…

That’s a really nice build.

Another possible build is to use a mini-pc and M.2 connections

You'll need a mini-pc with two M.2 slots, like this:

https://www.amazon.com/Beelink-SER7-7840HS-Computer-Display/...

And a riser like this:

https://www.amazon.com/CERRXIAN-Graphics-Left-PCI-Express-Ex...

And some courage to open it and rig the stuff in.

Then you can plug a GPU on it. It should have decent load times. Better than an eGPU, worse than the AM4 desktop build, fast enough to beat the M4 (once the data is in the GPU, it doesn't matter).

It makes for a very portable setup. I haven't built it, but I think it's a reasonable LLM choice comparable to the M4 in speed and portability while still being upgradable.

Edit: and you'll need an external power supply of at least 400W:)

Re: Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning

#126

Post by ziofill »

belter wrote: post #89
simonw wrote: post #9

The most interesting thing about this is the way it was trained using synthetic data, which is described in quite a bit of detail in the technical report: https://arxiv.org/abs/2412.08905 Microsoft haven't officially released the weights yet but there are unofficial GGUFs up on Hugging Face already. I tried this one: https://huggingface.co/matteogeniaccio/phi-4/tree/main I got it working with my LLM tool like this: l…

> it was trained using synthetic data Is this not supposed to cause Model collapse?

I may have misunderstood, but I think that it depends a lot on the existence of a validation mechanism. Programming languages have interpreters and compilers that can provide a useful signal, while for images and natural language there isn’t such an automated mechanism, or at least its not that straightforward.

Re: Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning

#127

Post by simonw »

chairhairair wrote: post #119
criddell wrote: post #110

Earlier quoted context omitted.

If you graded humanity on their reasoning ability, I wonder where these models would score? I think once they get to about the 85th percentile, we could upgrade the phrase to advanced reasoning. I'm roughly equating it with the percentage of the US population with at least a master's degree.

All current LLMs openly make simple mistakes that are completely incompatible with true "reasoning" (in the sense any human would have used that term years ago). I feel like I'm taking crazy pills sometimes.

Genuine question: what does "reasoning" mean to you?

Re: Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning

#128

Post by simonw »

belter wrote: post #113
fulafel wrote: post #91

Earlier quoted context omitted.

No.

Is this paper wrong? - https://arxiv.org/abs/2311.09807

It shows that if you deliberately train LLMs against their own output in a loop you get problems. That's not what synthetic data training does.

Re: Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning

#129

Post by accrual »

excerionsforte wrote: post #61

Looks like someone converted it for Ollama use already: https://ollama.com/vanilj/Phi-4

I've had great success with quantized Phi-4 12B and Ollama so far. It's as fast as Llama 3.1 8B but the results have been (subjectively) higher quality. I copy/pasted some past requests into Phi-4 and found the answers were generally better.

Re: Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning

#130

Post by evilduck »

michaelt wrote: post #103
evilduck wrote: post #56

Earlier quoted context omitted.

An optioned up minivan is also expensive but doesn’t cost as much as a firetruck. It’s expensive but still very much consumer hardware. A 3x4090 rig is more expensive and still consumer hardware. An H100 is not, you can buy like 7 of these optioned up MBP for a single H100.

In my experience, people use the term in two separate ways. If I'm running a software business selling software that runs on 'consumer hardware' the more people can run my software, the more people can pay me. For me, the term means the hardware used by a typical-ish consumer. I'll check the Steam hardware survey, find the 75th-percentile gamer has 8 cores, 32GB RAM, 12GB VRAM - and I'd better make sure my software w…

On the Steam Hardware Survey the average gamer uses a computer with a 1080p display too. That doesn't somehow make any gaming laptop with a 2k screen sold in the last half decade a non-consumer product. For that matter the average gaming PC on Steam is even above average relative to the average computer. The typical office computer or school Chromebook is likely several generations older doesn't have an NPU or discrete GPU at all.

For AI and LLMs, I'm not aware of any company even selling the models assets directly to consumers, they're either completely unavailable (OpenAI) or freely licensed so the companies training them aren't really dependent what the average person has for commercial success.

Post reply on HN