← Back to Explorer
On-Chain

T5-small (2019)

T5-small is a large language model released by Google, released under the apache-2.0 license, with a claimed knowledge cutoff of 2019-10-23. Its weights, configuration, and tokenizer files have been cryptographically hashed and permanently attested on Ethereum (Sepolia) by Weight Registry.

Description

Casts every NLP task -- translation, summarization, classification, question-answering -- as text-to-text generation via one encoder-decoder architecture. The 'small' checkpoint is 60M parameters, the smallest of five sizes released up to 11B, all sharing the same C4 (Colossal Clean Crawled Corpus) pretraining recipe.

Metadata

Type
LLM
Issuer
Google
License
apache-2.0
Size
—
Knowledge cutoff
2019-10-23
Source
https://huggingface.co/google-t5/t5-small
Revision
df1b051c49625cf57a3d0d8d3863ed4d13564fe4
Attester
0x6a94784135e413A474E6fA28d1A36C5d180B70c9

Hugging Face stats

24,227,473 downloads on Hugging Face · 639 likes · pipeline: translation · library: transformers

transformerspytorchtfjaxrustonnxsafetensorst5text2text-generationsummarization

Weight Hashes

Combined commitment: a Merkle root over the weights, config, and tokenizer hashes together (not a raw weights-only hash) -- see this project's v2 on-chain schema.
Combined SHA-2560xf34ef2155cc6eb3cbcf6b316278359908b3b196c6dfad3435c27d06ff0701c0d
Combined SHA3-2560x7ee49a0a58ceb94b8e5ab1d684f7f150d47054a822fb9d0d1e09a15f5325b2b7
Combined BLAKE30x6283daad15d10d68e021fa7fd202006983da5df2303554a86518b200e5d933d7

Per-file breakdown

Computed locally prior to attestation; the combined hash above is the canonical on-chain commitment.

Weights file
model.safetensors · 230.83 MB
SHA-256bd944e5f1b3ad9b70dd9d00010a517059e19265671076b8b0a4a58d9491842bc
SHA3-256762f6d214a507e28398d76a6c51699a152fb4914df157cc9939464ccd385bcb1
BLAKE38ec9044cd73290ad0b6a29d5459845c36c078ef928bb27cf222ddc9497354867
Config file
config.json · 1.18 KB
SHA-256530e25060e3a8d5f7b0fcf53bfea9f3601165161f3b1914676e98d97cf07bcf1
SHA3-256595d34e46ace9c4e829b8631f01d27c29f0b968f1f9dd00b9f0c4777c8318d3c
BLAKE348b11a2887c203f2ae2b0bd67fe633820a67d1536d72675a1569973ef0cac7e3
Tokenizer file
tokenizer.json · 1.32 MB
SHA-256d2acde0d8d71dd30a711834b07781b9c89feaac33fd332f60507699282740066
SHA3-256f59741b250e9b839620d2a976a2dd1f64b2d458c4375fd792baf4900effdd30b
BLAKE39ce04442387ff177fd52c14e1bd1901ba563d71e956ca2cffd39eeb3ef4bb820

Verify it yourself

curl -L -o "model.safetensors" "https://huggingface.co/google-t5/t5-small/resolve/df1b051c49625cf57a3d0d8d3863ed4d13564fe4/model.safetensors"
sha256sum "model.safetensors"

Expected SHA-256: bd944e5f1b3ad9b70dd9d00010a517059e19265671076b8b0a4a58d9491842bc