Viewing profile — varunvummadi

[flagged]

The easiest is to use vllm ( https://github.com/vllm-project/vllm ) to run it on a Couple of A100's, and you can benchmark this using this library ( https://github.com/EleutherAI/l…

It beats the old GPT4 version in lmsys benchmark you can check it out here https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboar... but Command R is commercially licensed We…

Not sure trying to download the torrent and checking it out

They Just announced their new model on Twitter, which you can download using torrent

Should appreciate the dedication of the person who made this website, haha

So please let me know if I am wrong are you guys running a batch size of 1 in 500 GPU's? then why are the responses almost instant if you guys are using batch size 1 and also when …

That is true cursor extension is awesome