title

Language Model Zoo 🦍 - #18 by jeremy - Part 2 & Alumni (2018) - fast.ai Course Forums

charset

utf-8

description

This thread’s objective is to discuss the ULMFiT implementations in different languages and share our roadblocks and approaches. A word to newcomers This thread is huge, and can be overwhelmed, but there is an easy way …

generator

Discourse 3.5.0.beta5-dev - https://github.com/discourse/discourse version eff31e0d42c535ee115317f5b63ff70d90097911

theme-color

#fff

og:site_name

fast.ai Course Forums

og:type

website

og:image

https://forums.fast.ai/uploads/default/original/3X/b/3/b395de7a2ba00b82865031c97a8cadf3d80e71e5.png

og:url

https://forums.fast.ai/t/language-model-zoo-gorilla/14623/18

og:title

Language Model Zoo 🦍

twitter:card

summary

twitter:image

https://forums.fast.ai/uploads/default/original/3X/b/3/b395de7a2ba00b82865031c97a8cadf3d80e71e5.png

twitter:url

https://forums.fast.ai/t/language-model-zoo-gorilla/14623/18

twitter:title

Language Model Zoo 🦍

twitter:description

A note to those folks building langage models: there’s no reason to go beyond 100 million tokens - in my experiments it didn’t help. So if your corpus is bigger than that, remove some of the smaller articles (for instance) until the corpus is down to that size. Really large corpuses are a pain to work with, and don’t have any benefits I saw.

position

1

headline

Language Model Zoo :gorilla:

datePublished

2018-04-08T02:58:13Z

articleSection

Part 2 & Alumni (2018)

keywords

alternate nofollow

https://forums.fast.ai/t/language-model-zoo-gorilla/14623.rss

apple-touch-icon

https://forums.fast.ai/uploads/default/optimized/3X/b/3/b395de7a2ba00b82865031c97a8cadf3d80e71e5_2_180x180.png

canonical

https://forums.fast.ai/t/language-model-zoo-gorilla/14623

icon

https://forums.fast.ai/uploads/default/optimized/3X/b/3/b395de7a2ba00b82865031c97a8cadf3d80e71e5_2_32x32.png

url

https://forums.fast.ai/u/lesscomfortable