OLMo-2-1124-7B is a large language model released by Allen Institute for AI, released under the Apache-2.0 license, with a claimed knowledge cutoff of 2024-11-26. Its weights, configuration, and tokenizer files have been cryptographically hashed and are queued for on-chain attestation by Weight Registry.
Description
Second-generation OLMo, trained on ~5T tokens (OLMo-Mix-1124 then Dolmino-Mix-1124 mid-training) with an improved architecture and training recipe over the original OLMo-7B, while keeping AI2's full open-data/open-code transparency commitment.
Metadata
Hugging Face stats
69,469 downloads on Hugging Face · 70 likes
Weight Hashes
Weights file
SHA-2566826d5b3eecf502430ab9c09f7b9520f7121c634d33b737b98b5db7263117054
SHA3-256348f20da44f93450dd7ed0c475dfacb76589c2d3449625e6a01095820583d679
BLAKE3ba2a653643e205190259a5dbedd8a5f3dd7921830d6216d392508bf75e1bcdb3
Config file
SHA-256f1e210de0ba704c579768c154bf57e36e170868ffecb060a6e0d3f2e6b0b9710
SHA3-256e6604c3c22d984ee8a73faaa92b63607f48ed2cf54beedc087ae70256026b04b
BLAKE375dcdecc2ba3445187a01bc9ab35c95d0bb6d0500f375b2e2e201bedb066cbe9
Tokenizer file
SHA-25673fd5254624f39a88e3faac6a8e11300fc3c735ed37880d4f4f08db898eaecca
SHA3-25668f02d9ed7613e9917107f61db52bd3fb20740df819ed1b86e0bb0a955e66d30
BLAKE35be5a0b8b0ed26eaac3df3189a8c100e6e2df1e34cf360ef899a796008708624
Verify it yourself
Download the file(s) from the source below, then hash them locally (sha256sum <file> on Linux/macOS, certutil -hashfile <file> SHA256 on Windows) and compare the output against the hash(es) shown above.