WizardLM-2-8x22B is a large language model released by Microsoft, released under the apache-2.0 license, with a claimed knowledge cutoff of 2024-04-30. Its weights, configuration, and tokenizer files have been cryptographically hashed and are queued for on-chain attestation by Weight Registry.
Description
WizardLM-2 8x22B, Microsoft AI's most advanced Wizard model at release, demonstrating highly competitive performance vs leading proprietary models and outperforming existing open-source models. Microsoft removed the original repo within hours of release (cited missing toxicity testing); this entry hashes the community-preserved mirror, which is itself a case study in why an immutable weight registry matters.
Metadata
Hugging Face stats
10,645 downloads on Hugging Face · 416 likes · pipeline: text-generation · library: transformers
Weight Hashes
Weights file
SHA-256344a906810b26288393aff266dde161d176fc6c4fb70f4ba4582d18cab71cfbf
SHA3-256727f63352c14416be22381c839b9abcc19e77937ed15d043debf8f3e3fb0e9ff
BLAKE38d405156f3823cb7ccb34cdff17d1cf1856c65278e5341ad25bb3e9682c1d1d8
Config file
SHA-2568241c0f3bea01add64c800919cf3b179ec5efbd709afe17986f952c64821d1e5
SHA3-25686227856c6a309066adbca793570fe8d6a3c46d8ce6027926508ca103e2d1d64
BLAKE34a51a5cd6d3578821ae763ff9bf16b91431f78b2948b118e4dfdfc18f2174670
Tokenizer file
SHA-256dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
SHA3-2567821ee4866c5d0bed0c000c85e3fed39ca684266b3f5a4ba370c235151790aa3
BLAKE37d06176d89e0c491987309df1c4293e286addeeb40047e0dd26466ff8f0d12f6
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.