What? let’s try not to go full forehead into hype.

SVGs would be an awfully poor analogy for the physical world…

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.

I'd be interested for any LLM emitting any kind of text-to-picture instructions to get results that are beyond a kindergartner-cardboard-cutout levels of art.

https://gist.github.com/uschen/38fc65fa7e43f5765a584c6cd24e1...

Copied SVG from gist into figma, added dark gray #444444 background, exported as PNG 1x.

You can click on the little info icon on Hugging Face to see that directly.

For https://huggingface.co/matteogeniaccio/phi-4/tree/main?show_... that's this:

  {% for message in messages %}{% if
  (message['role'] == 'system')
  %}{{'<|im_start|>system<|im_sep|>' +
  message['content'] + '<|im_end|>'}}{%
  elif (message['role'] == 'user')
  %}{{'<|im_start|>user<|im_sep|>' +
  message['content'] +
  '<|im_end|><|im_start|>assistant<|im_sep|>'}}{%
  elif (message['role'] == 'assistant')
  %}{{message['content'] + '<|im_end|>'}}{%
  endif %}{% endfor %}

For diffusion-based image generators training only on synthetic data over repeated model training can cause model collapse as errors in the output can amplify in the trained model. It's usually the 2nd or 3rd model created this way (with output of the previous used as input for the first) for it to collapse.

It was found that using primary data along side synthetic data avoided the model collapse. Likewise, if you also have some sort of human scoring/evaluation you can help avoid artefacts.

As far as I can tell model collapse happens when you deliberately train LLMs on low quality LLM-generated data so that you can write a paper about it.

Since there are GGUFs now so someone must have released some weights somewhere.

I've just assumed it's down to how it was trained, but no expert.

If only those models supported anything other than English

Did you mean _external gpu_?

Choose any 12GB or more video card with GDDR6 or superior and you'll have at least double the performance of a base m4 mini.

The base model is almost an older generation. Thunderbolt 4 instead of 5, slower bandwidths, slower SSDs.

Some people do place value on running locally, and I'm not against then for it, but realistically no 70B class model has the amount of general knowledge or understanding of nuance as any recent GPT-4 checkpoint.

That being said these models are still very strong compared to what we had a year ago and capable of useful work

1) Realize when it's reached an impasse, then backtrack and explore alternatives

2) Recognize when no further progress towards the goal appears possible, and switch from exploiting existing knowledge to exploring/acquiring new knowledge to attempt to proceed. An LLM has limited agency, but could for example ask a question or do a web search.

In either case, prediction failure needs to be treated as a learning signal so the same mistake isn't repeated, and when new knowledge is acquired that needs to be remembered. In both cases this learning would need to persist beyond the current context in order to be something that the LLM can build on in the future - e.g. to acquire a job skill that may take a lot of experience/experimentation to master.

It doesn't matter what you call it (basic or advanced), but it seems that current attempts at adding reasoning to LLMs (e.g. GPT-o1) are based around 1), a search-like strategy, and learning is in-context and ephemeral. General animal-like reasoning needs to also support 2) - resolving impasses by targeted new knowledge acquisition (and/or just curiosity-driven experimentation), as well as continual learning.

I feel like I'm taking crazy pills sometimes.