← Back to Explorer
Pending

gpt2-large (2019)

gpt2-large is a large language model released by OpenAI, released under the MIT-ish license, with a claimed knowledge cutoff of 2019-08-20. Its weights, configuration, and tokenizer files have been cryptographically hashed and are queued for on-chain attestation by Weight Registry.

Description

Larger (774M) GPT-2 size; the smaller 124M size is already separately attested on-chain in this registry.

Metadata

Type
LLM
Issuer
OpenAI
License
MIT-ish
Size
3.02 GB
Knowledge cutoff
2019-08-20
Source
https://huggingface.co/openai-community/gpt2-large
Revision
32b71b12589c2f8d625668d2335a01cac3249519

Hugging Face stats

1,240,018 downloads on Hugging Face · 360 likes · pipeline: text-generation · library: transformers

transformerspytorchtfjaxrustonnxsafetensorsgpt2text-generationen

Weight Hashes

Weights file
model.safetensors · 3.02 GB
SHA-2565f47f3e12f91cd33b662ce7e433b6150ad5512b5884a2cee961b50e9c3bbebce
SHA3-2561b41df1073f1b84caed169e6adaef0afcbd85fd5b706167a2f00495d50433369
BLAKE31e6af70d3f4285f5c130783affd0c3950b1d41619a897102acc17a558caf688c
Config file
config.json · 666 B
SHA-2567fccdcfd6622055342a734c663ee0b61ff4fd697f42467595df0bf4448c8c170
SHA3-25615b199237523504b9e3f1bccf1bdf4075a6643a9d7c9675ecee4f9c494277d3c
BLAKE3ae7f4adaaf02c683010447c54f71b1f30dc2e129c17983515bab6cc065f27fe7
Tokenizer file
tokenizer.json · 1.29 MB
SHA-2568414cab924d8b9b33013f0d221c5862f365ee9be39c5c2bfae8a5a9e970478a6
SHA3-256a76dcbb920e1161c1512f6139329e4cbac4f070883b4e767055037e1a0c9b715
BLAKE31f9b61de3382db2e111c702730ef4ad5b12788d3c040db87936da6c7f988f861

Verify it yourself

curl -L -o "model.safetensors" "https://huggingface.co/openai-community/gpt2-large/resolve/32b71b12589c2f8d625668d2335a01cac3249519/model.safetensors"
sha256sum "model.safetensors"

Expected SHA-256: 5f47f3e12f91cd33b662ce7e433b6150ad5512b5884a2cee961b50e9c3bbebce

Anomalies Flagged

  • other weight-like files present but not hashed: ['pytorch_model.bin']