HyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAI

Language Modelling On C4

Metrics

Perplexity
Steps
TPUv3 Hours

Results

Performance results of various models on this benchmark

Model Name
Perplexity
Steps
TPUv3 Hours
Paper TitleRepository
T5++12.691M16.5KPrimer: Searching for Efficient Transformers for Language Modeling
Zeropoint LLM.int8 13B (vector-wise + decomp)12.45--LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
Original T513.251M15.7KPrimer: Searching for Efficient Transformers for Language Modeling
N-Grammer 343M14.79--N-Grammer: Augmenting Transformers with latent n-grams
LLM.float32 2.7B14.43--LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
LLM.float32 1.3B15.91--LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
Primer12.351M17.3KPrimer: Searching for Efficient Transformers for Language Modeling
N-Grammer 288M15.01--N-Grammer: Augmenting Transformers with latent n-grams
LLM.float32 6.7B13.3--LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
0 of 9 row(s) selected.