$\infty$-former: Infinite Memory Transformer

Benchmark Model Rank Results
language-modelling-on-wikitext-103[?]-former (SM)#18Test perplexity: 16.61
language-modelling-on-wikitext-103-former (SM)#19Test perplexity: 16.61
language-modelling-on-wikitext-103โˆž-former (Sticky memories + initialized GPT-2 Small)#20Test perplexity: 16.61
language-modelling-on-wikitext-103โˆž-former (initialized GPT-2 Small)#21Test perplexity: 16.64
language-modelling-on-wikitext-103[?]-former (Sticky memories)#58Test perplexity: 24.22
language-modelling-on-wikitext-103\infty-former (Sticky memories)#59Test perplexity: 24.22
language-modelling-on-wikitext-103โˆž-former (Sticky memories)#60Test perplexity: 24.22