RT @jacksonfall: I gave GPT-4 a budget of $100 and told it to make as much money as possible.
I'm acting as its human liaison, buying anything it says to.
Do you think it'll be able to make smart investments and build an online business?
Follow along 👀 https://t.co/zu4nvgibiK
RT @niw: Run your chat app locally using Alpaca-LoRA on iOS devices. 🦙
Based on amazing work from directly @antimatter15’s alpaca.cpp, @ecjwg’s alpaca-lora, @ggerganov’s llma.cpp and many others.
https://t.co/AJmkg8hsuY
RT @rainisto: Absolutely epic experimental film. Another glimpse of the future. Team size - one?! https://t.co/6TeTVXEmMQ
RT @TomLikesRobots: @IntuitMachine Check this out. First few hours/minutes and people have already started using it to tell stories. The coherence isn't that far behind Gen1. https://t.co/uGShETOFmf
シタル氏の予測、LLMはラージ(大規模)じゃなくなってくかも。巨大パラメータのGPT-4はすごいけど、2022年の研究でLLMのパラメータに対する性能の効率がブチ上がった。微調整(T0,FLAN)、Better objectives (UL2, FIM,… https://t.co/t6ym4aMnCg
RT @toyxyz3: If you increase the weight, you can adjust the character's face more strongly, but the face shape is deformed. https://t.co/EEUgXCJzse
RT @kuronagirai: ひとまずは4090機でCUDA11.8+Pytorch2.0+WSL2で環境構築完了!
出力テストはうまくいったかも?
でも学習開始しようとすると非印刷可能文字が含まれてるってエラーは本当に何なんだろう…
データセットは3060Ti機の中にあったものと全く同じなのに… https://t.co/6RLOoRik0E
RT @toyxyz3: https://t.co/O1bO6kaWzN
ゲッ!Animelikeモデル!これいいね!なにがって、画像AIのイラストは綺麗だけど塗りがリッチすぎる傾向があったけど、これはアニメっぽい見やすい塗りだ。マンガにも向いてると思う。ただ、「商用利用しないで」みたいな事描いてるね。え~?2.5Dと2Dのモデルがある →RT https://t.co/ga4OxlgWNY
RT @toyxyz3: https://t.co/LWHpUeZpUV
RT @_kzr: I created a proof-of-concept integration of ChatGPT into Unity Editor. You can edit your Unity projects using natural language prompts. https://t.co/suLrE0tEEB https://t.co/CnaD5zp744