Albert Avetisian
Albert Avetisian
nvm, you can reverse-convert [these seeds](https://github.com/hmartiro/riffusion-inference/tree/main/seed_images) back into audio to hear them. but still would be nice to have a quick preview of each of the seeds (eventually being able...
happening ?
consider a section here (or separate section) for observability tools, some examples: - [isolated logs in Azure](https://github.com/aavetis/azure-openai-logger) (i made this) - [Helicone](https://github.com/Helicone/helicone) - [llm.report](https://github.com/dillionverma/llm.report)
thoughts on adding Apple's proper [mobileclip](https://github.com/apple/ml-mobileclip) instead? > Our smallest variant MobileCLIP-S0 obtains similar zero-shot performance as [OpenAI](https://arxiv.org/abs/2103.00020)'s ViT-B/16 model while being 4.8x faster and 2.8x smaller. MobileCLIP-S2 obtains better...
this feature just made it into mainline vs code. https://x.com/ashtom/status/1933229635816599917?s=46&t=Wma7QkpS_A5Fot9jPgsmQg
based on this issue, looks like you need to prepend the model with `openai/` so it believes it is openai api compatible https://github.com/crewAIInc/crewAI/issues/1456