← Back to context Comment by throwa356262 1 day ago Regarding #2https://news.ycombinator.com/item?id=48529544 3 comments throwa356262 Reply xiphias2 19 hours ago This should be at the top: they uploaded the wrong model, they fixed it jwitthuhn 16 hours ago They did upload the wrong model but as of the time of writing they have not fixed it. Right now, 12 hours after they took the old one down, there is simply no model present in their huggingface repo. xiphias2 15 hours ago I guess they will upload it later, it seems like an honest mistake to me.Anyways SwiTransformer paper looks interesting and doing a post training to optimize for it looks interesting as well.
xiphias2 19 hours ago This should be at the top: they uploaded the wrong model, they fixed it jwitthuhn 16 hours ago They did upload the wrong model but as of the time of writing they have not fixed it. Right now, 12 hours after they took the old one down, there is simply no model present in their huggingface repo. xiphias2 15 hours ago I guess they will upload it later, it seems like an honest mistake to me.Anyways SwiTransformer paper looks interesting and doing a post training to optimize for it looks interesting as well.
jwitthuhn 16 hours ago They did upload the wrong model but as of the time of writing they have not fixed it. Right now, 12 hours after they took the old one down, there is simply no model present in their huggingface repo. xiphias2 15 hours ago I guess they will upload it later, it seems like an honest mistake to me.Anyways SwiTransformer paper looks interesting and doing a post training to optimize for it looks interesting as well.
xiphias2 15 hours ago I guess they will upload it later, it seems like an honest mistake to me.Anyways SwiTransformer paper looks interesting and doing a post training to optimize for it looks interesting as well.
This should be at the top: they uploaded the wrong model, they fixed it
They did upload the wrong model but as of the time of writing they have not fixed it. Right now, 12 hours after they took the old one down, there is simply no model present in their huggingface repo.
I guess they will upload it later, it seems like an honest mistake to me.
Anyways SwiTransformer paper looks interesting and doing a post training to optimize for it looks interesting as well.