Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Scalable MatMul-Free Language Modeling.
it is super easy to try it out, the 2.7B, 1.3B, 0.37B models are on huggingface, and the generate.py example just works if you have triton 2.2 installed
There are no comments on this comment yet.
it is super easy to try it out, the 2.7B, 1.3B, 0.37B models are on huggingface, and the generate.py example just works if you have triton 2.2 installed