iEmoji Feeds @Victor Sanh (SanhEstPasMoi)
1.
Victor Sanh
@SanhEstPasMoi
GPT-4 is out!!
- it is incredible
- it is multimodal (can see)
- it is on trend w.r.t. scaling laws
- itโฆ twitter.com/i/web/status/1โฆ
- it is incredible
- it is multimodal (can see)
- it is on trend w.r.t. scaling laws
- itโฆ twitter.com/i/web/status/1โฆ
14 Mar 23
copy & paste +upvote -downvote ๐ GPT-4 is out!!
- ๐ it is incredible
- ๐ it is multimodal (can see)
- ๐ฎ it is on trend w.r.t. scaling laws
- ๐ฅ itโฆ https://t.co/ZQpu3olOBj
2.
Victor Sanh
@SanhEstPasMoi
Fine tune a 20B Language Model with RLHF using a 24GB consumer GPU?
It is now possible using TRL + PEFT!
Check ouโฆ twitter.com/i/web/status/1โฆ
It is now possible using TRL + PEFT!
Check ouโฆ twitter.com/i/web/status/1โฆ
Retweet of status by @younesbelkada
09 Mar 23
copy & paste +upvote -downvote Fine tune a 20B Language Model with RLHF using a 24GB consumer GPU? ๐คฏ
It is now possible using TRL + PEFT!
Check ouโฆ https://t.co/P4R4b79P1g
3.
4.
5.
6.
7.
Victor Sanh
@SanhEstPasMoi
We release the public beta for bnb-int8๐ช for all @huggingface models, which allows for Int8 inference without perfโฆ twitter.com/i/web/status/1โฆ
Retweet of status by @Tim_Dettmers
10 Aug 22
copy & paste +upvote -downvote We release the public beta for bnb-int8๐ช for all @huggingface ๐คmodels, which allows for Int8 inference without perfโฆ https://t.co/kCFGTvbfSd
Victor Sanh
@SanhEstPasMoi
4 challenging speech tasks, 102 spoken languages: can one model solve them all?
Introducing @GoogleAI's XTREME-โฆ twitter.com/i/web/status/1โฆ
Introducing @GoogleAI's XTREME-โฆ twitter.com/i/web/status/1โฆ
Retweet of status by @huggingface
31 Mar 22
copy & paste +upvote -downvote ๐4 challenging speech tasks, 102 spoken languages: can one model solve them all? ๐คฏ
Introducing @GoogleAI's XTREME-โฆ https://t.co/LAAbLizCst
Victor Sanh
@SanhEstPasMoi
"Hugging Face (yes, that really is the name)"
A Survey of Deep Learning for Scientific Discovery, fromโฆ twitter.com/i/web/status/1โฆ
A Survey of Deep Learning for Scientific Discovery, fromโฆ twitter.com/i/web/status/1โฆ
28 Mar 20
copy & paste +upvote -downvote "Hugging Face (yes, that really is the name)" ๐ค๐ค๐ค
A Survey of Deep Learning for Scientific Discovery, fromโฆ https://t.co/l8ek6JEdX0
Victor Sanh
@SanhEstPasMoi
@sam_shleifer @huggingface Welcome on board Sam!
28 Jan 20
copy & paste +upvote -downvote @sam_shleifer @huggingface Welcome on board Sam! ๐ค๐ฅ
Victor Sanh
@SanhEstPasMoi
This is SO meta
We trained a generative language model on a dataset of ArXiv NLP papers. You can now get a neuraโฆ twitter.com/i/web/status/1โฆ
We trained a generative language model on a dataset of ArXiv NLP papers. You can now get a neuraโฆ twitter.com/i/web/status/1โฆ
Retweet of status by @huggingface
05 Sep 19
copy & paste +upvote -downvote This is SO meta ๐ค
We trained a generative language model on a dataset of ArXiv NLP papers. You can now get a neuraโฆ https://t.co/zw71FQ9Lxb
8.
Victor Sanh
@SanhEstPasMoi
We ported @OpenAI's GPT-2 to run on-device (using Swift and CoreML on iOS)
Large transformers models can nowโฆ twitter.com/i/web/status/1โฆ
Large transformers models can nowโฆ twitter.com/i/web/status/1โฆ
26 Jul 19
copy & paste +upvote -downvote ๐ฆ We ported @openai's GPT-2 to run on-device (using Swift and CoreML on iOS) ๐ฅ๐ฅ
Large transformers models can nowโฆ https://t.co/0G8ItrnI2s
...but wait! There's more!
1.
fakhright
@fakhright
astaghfirullah peng.krim guaaaaaaaa..............a *salto sambil solat*
14 Jan 13
copy & paste +upvote -downvote astaghfirullah peng.krim guaaaaaaaa..............a *salto sambil solat* ๐๐๐