News for hackers. Stuff that matters.
Re:Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion by refulgentis on Wednesday September 13, 2023 @02:32PM (#37499951)
I'm all ears. I was "in the room" from 2019 on. Can't name one art model you could run on your GPU from a FAANG or OpenAI before SD, and can't name one LLM with public access before ChatGPT, much less weights available till LLaMA 1.

But please, do share.

Re:Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion by hofstee on Wednesday September 13, 2023 @04:11PM (#37501126)
Re:Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion by thewataccount on Wednesday September 13, 2023 @05:13PM (#37501813)
Openai - GPT2 2019 - https://openai.com/research/gpt-2-1-5b-release

Google - T5 - Feb 2020 - https://blog.research.google/2020/02/exploring-transfer-lear...

Both of these were and still are used heavily for on-going research and T5 has been found to be decently useful when fine-tuned.

Weights were available for both.

Re:Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion by refulgentis on Wednesday September 13, 2023 @05:35PM (#37502021)
Re:Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion by smoldesu on Wednesday September 13, 2023 @05:17PM (#37501845)
> Can't name one art model you could run on your GPU from a FAANG or OpenAI before SD

Google published dozens to promote Tensorflow:

https://experiments.withgoogle.com/font-map https://experiments.withgoogle.com/sketch-rnn-demo https://experiments.withgoogle.com/curator-table https://experiments.withgoogle.com/nsynth-super https://experiments.withgoogle.com/t-sne-map

The list goes on. Many are source-available with weights too.

> can't name one LLM with public access before ChatGPT, much less weights available till LLaMA 1.

Do any of these ring a bell?

- DistilBERT/MobileBERT/DeBERTa/RoBERTa/ALBERT

- FNet

- GPT2/GPT-Neo/GPT-J

- Marian

- MBart

- M2m100

- NLLB

- Electra

- T5/LongT5/T5-flan

- XLNet

- Reformer

- ProphetNet

- Pegasus

That's not comprehensive but may be enough to jog your memory.

Re:Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion by refulgentis on Wednesday September 13, 2023 @05:28PM (#37501964)
I understand your point.

The gap in communication is we don't mean _literally_ no one _ever_ open-sourced models. I agree, that would be absurd. [1]

Companies, quite infamously and well-understood, _did_ hold back their "real" generative models, even from being available for pay.

Take a stab at a literal definition: - post-GPT2 LLMs (ex. PALM, PALM2) - art like DaLL-E, Imagen, Parti

Loosely, we had Disco Diffusion for art, and GPT-3 for LLMs, and then Dall-E, then Midjourney. That was over an _entire year_, and the floodgates on private ones didn't open till post SD/ChatGPT.

[1] thank you for the lengths you went to highlight the best over a considered span of time, I would have just said something snarky :)

[2] I did not realize FLAN was open-sourced a month before ChatGPT, that's fascinating: we're stretching a bit, beyond that, IMHO: the BERTs aren't recognizable as LLMs.

Re:Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion by smoldesu on Wednesday September 13, 2023 @05:36PM (#37502043)
All good. I've also been working on LLMs since 2019-ish, so I wanted to toss a hat in the ring for the underrepresented transformer models. They were cool (eg. dumb), fast and worked better than they had any right to. In a lot of ways they are the ancestors of ChatGPT and Llama, so it's important to at least bring them into the discussion.
Re:Stable Audio: Fast Timing-Conditioned Latent Audio Diffusion by astrange on Wednesday September 13, 2023 @05:45PM (#37502157)
> Can't name one art model you could run on your GPU from a FAANG or OpenAI before SD

CLIP could be used as an image generator, slowly.

> and can't name one LLM with public access before ChatGPT, much less weights available till LLaMA 1

InstructGPT was available on OpenAI playground for months before ChatGPT and was basically as capable as GPT3, people were really missing out. Don't know any good public models though.