Mistral-7B-Instruct-v0.2 is a large language model released by Mistral AI, released under the apache-2.0 license, with a claimed knowledge cutoff of 2023-12-11. Its weights, configuration, and tokenizer files have been cryptographically hashed and permanently attested on Ethereum (Sepolia) by Weight Registry.
Description
Instruction-tuned Mistral 7B, version 0.2, released fully permissively.
Metadata
Hugging Face stats
1,790,391 downloads on Hugging Face · 3,235 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-2560xb541c84222f43a58b4037e15257ea55d3e0200d6450d412f721e2b55e381e510
Combined SHA3-2560xd1182e14b3cd9e61bb4ad8c35f5fe346fe233b842f39beee6255c0437c865826
Combined BLAKE30xc8fd89b75002e6d3487fabad8c8acf55574cbc728ebdcd025a11b610da62dd25
Per-file breakdown
Computed locally prior to attestation; the combined hash above is the canonical on-chain commitment.
Config file
SHA-2562e97da1b1d2b7e7669f0991c186904538c27d4ea56c4fc74e89215e2b2013922
SHA3-256a12ddac0115f3c2a6a5a3948a3ac99c55a4fa2a422b28d8642fe66c68481cc65
BLAKE30318948eb291e251cc85e68fd762d76c4072f3a740c6af54b73af0954facb5f8
Tokenizer file
SHA-25611c08db21487c885d8c792180f0be237f6a261b89a46f128a6a80a3aa4bd1720
SHA3-2560e81dce2e2032ac2dfc26adf7a1fe0f6a685569971191e5b2968a81c1b3c10f5
BLAKE30d8c8f93f99c57d58d54ea6c81562579dd5a04de4bd1f8ff900250ec69b34a0e
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.