varunvummadi
Joined 6 years ago
Karma
375
Submissions
15
Member since
Aug 31
Cofounder of Giga ML
message me on twitter : https://twitter.com/varunvummadi
View on Hacker NewsRecent submissions
Comment · 2 years ago
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/lm-evaluation-harness)
Comment · 2 years ago
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 can assume that mistral will do a better job.
Comment · 2 years ago
Not sure trying to download the torrent and checking it out
Comment · 2 years ago
They Just announced their new model on Twitter, which you can download using torrent
Comment · 2 years ago
Should appreciate the dedication of the person who made this website, haha
Comment · 2 years ago
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 can we expect bring your own fine tuned models kind of thing. Thanks!
Comment · 3 years ago
That is true cursor extension is awesome