Improving language models by retrieving from trillions of tokens
Milestone Papers
Improving language models by retrieving from trillions of tokens

(2021-12) Retro by DeepMind

Paper
(2021-12) Retro by DeepMind

Relevant Sites

An empirical analysis of compute-optimal large language model training

(2022-04) Chinchilla by DeepMind

Mistral 7B

(2023-10) Mistral 7B by Mistral

LLaMA: Open and Efficient Foundation Language Models

(2023-02) LLaMA by Meta

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

(2021-01) Switch Transformers by Google

Language Models are General-Purpose Interfaces

(2022-06) METALM by Microsoft

Visual Instruction Tuning

(2023-04) LLaVA by UW–Madison&Microsoft

Leave a Reply

Your email address will not be published. Required fields are marked *