Semanlink - LMs: context length ; NLP@Meta AND NLP: pretraining

Printer friendly

Search Tag:

Search Doc:

Preferences...

Tag Cloud

Arxiv Doc - LM: tokenization - LMs: context length - Long documents - NLP@Meta - Transformers - Tweet -

LMs: context length ; NLP@Meta AND NLP: pretraining

Common descendants

2 Documents

Philipp Schmid sur X : “YaRN” allows you to scale LLMs like llama 2 to over 100k context!...

Tags:

2023-09-01 About

[2305.07185] MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers

Tags:

2023-07-01 About