From 44acd4687ff40b39683dcab2f01fb784268dbb1d Mon Sep 17 00:00:00 2001 From: Phil Wang Date: Fri, 30 Dec 2022 10:12:52 -0800 Subject: [PATCH] todo --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index f019f96..450d7f3 100644 --- a/README.md +++ b/README.md @@ -141,6 +141,7 @@ answer = trainer.generate(2048, prompt = prompts[0], num_samples = 10) # (<= 204 - [ ] allow for finetuning penultimate N layers only in either actor or critic, assuming if pretrained - [ ] incorporate some learning points from Sparrow, given Letitia's video - [ ] simple web interface with django + htmx for collecting human feedback +- [ ] equip with the best attention ## Citations