Re:Introducing ChatGPT and Whisper APIs
by vishal0123 on Thursday March 02, 2023 @05:12AM
(#34994028)
From the paper
> For contexts and models with d_model > n_ctx/12, the context-dependent computational cost per token is a relatively small fraction of the total compute.
For GPT3, n_ctx is 4096 and d_model is 12228 >> 4096/12.
> For contexts and models with d_model > n_ctx/12, the context-dependent computational cost per token is a relatively small fraction of the total compute.
For GPT3, n_ctx is 4096 and d_model is 12228 >> 4096/12.