Vaibhav (VB) Srivastav
@reach_vb
chief get-shit-done officer @huggingface | F1 fan | Here for @at_sofdog’s wisdom | *opinions my own
I did this. Fuck what anyone else says, just put the pedal to the metal and BUILD. Push spaghetti code. Nobody cares about OOPs. Doesn’t matter what anyone thinks. Just keep on doing. Document in public. Don’t listen to the haters. Release more than you refactor. Just keep…
Just do stuff
Absolutely love playing with this! ❤️
NEW: Onboarding experience on Hugging Face! - Experience the SoTA LLMs and Text to Image models directly 🤩 Really helps contextualise how to use these models and what they are capable of as of today Ofcourse powered by our Inference Providers!
Clarification: This was a cheeky way to say that the latest release from @Alibaba_Qwen sets a new milestone/ hill to climb for rest of the field. We now have an open weights model competing with Opus 4 - the models will only get better and better from here.
This is the dumbest open source models ever will be
Qwen COOKED - beats Kimi K2 and competitive to Claude Opus 4 at 25% total parameters 🤯
loosely consider num downloads of openai python package as a leading indicator of AI adoption
It’s the weekend, don’t forget to take it easy, chat!
You asked we delivered! Hugging Face Inference Providers is now fully OpenAI client compatible! 🔥 Simply append the provider name to the model ID OpenAI client is arguably the most used client when it comes to LLMs, so getting this right is a big milestone for the team! 🤗