opt-125m is a large language model released by Meta, released under the other license, with a claimed knowledge cutoff of 2022-05-03. Its weights, configuration, and tokenizer files have been cryptographically hashed and permanently attested on Ethereum (Sepolia) by Weight Registry.
Description
Smallest size in Meta's OPT family, an attempt to openly reproduce GPT-3-class capability with detailed training logs.
Metadata
Hugging Face stats
6,854,124 downloads on Hugging Face · 324 likes · pipeline: text-generation · library: transformers
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-2560xd57ab093c6317a4c2d6cfe4acd29f99d046d56f4b61f11e686dc7e2cfd13c663
Combined SHA3-2560x9ac03b8c863bf89c22ef70ba57e24fcf856a2862f3c5286b37e150aee9afc49c
Combined BLAKE30x554c7b668a6a8aa169d1f30a9584e752c2da5167b6d4c4054047505fbe3a4336
Per-file breakdown
Computed locally prior to attestation; the combined hash above is the canonical on-chain commitment.
Weights file
SHA-2562d74da6615135c58cf3cf9ad4cb11e7c613ff9e55fe658a47ab83b6c8d1174a9
SHA3-2560901d3f912f707649a6ff3c9fc39542378bc5d11df4f69567d2daa758b13edd0
BLAKE3eec3d603b848a75806a73137616aea3f74e8dbc3f5cb38709c6ecd16a403e89f
Config file
SHA-25654162c9cd0377110df1859dfabebb106fc0988c8aadb88207ce1ee0d34985df6
SHA3-2569f039930ca7ed353522ddd279687956a4c16841ef47650cf2b80fb8c8d1a2d30
BLAKE320193a683619678cc1ea4c269484f8b71d702389d6aeee745c9942f69a3f289d
Tokenizer file
SHA-25606b4d46c8e752d410213d9548eb27a54db70fda0319b6271fb8d59dead5e1cab
SHA3-2560fc6228de99a611bb657e8af5658f3159343128bc9ac37579f1b4c5f5fd0c57a
BLAKE31eb42310d7a2bf1a44ceba688bb79c3bc03e68513317e7ac5c7d1a16b6c8a43a
Verify it yourself
curl -L -o "pytorch_model.bin" "https://huggingface.co/facebook/opt-125m/resolve/27dcfa74d334bc871f3234de431e71c6eeba5dd6/pytorch_model.bin" sha256sum "pytorch_model.bin"
Expected SHA-256: 2d74da6615135c58cf3cf9ad4cb11e7c613ff9e55fe658a47ab83b6c8d1174a9