Transformer, the model architecture of the year comes to Computer Visionchengh.medium.com2 ポイント·投稿者 satorii·6 年前·0 コメント
satorii·5 年前·議論Interesting findings! Not sure about whether it is within certain research communities or a broader trend.But Clip cloud be a good plug-in for nowadays writings/design then, something like Clip empowered unsplash.
satorii·6 年前·議論Cool! I will drop you a message or catch up with you on openai-api slack.There are a couple of features we see GPT3 stands out and potentially benefits the product features.Currently we are evaluating the end to end quality and cost versus our traditional ML based recommendation and semantic search pipeline.
satorii·6 年前·議論assume each prediction use 1000 tokens (including both input prompt and output text), then 100k tokens -> 100 predictions
satorii·6 年前·議論Thanks for pointing out the errors. I got them fixed in the blog. This is also a good use case of GPT3, checking grammar and spelling. I might build an application for this.