← Back to Explorer
On-Chain

Yi-6B (2023)

Yi-6B is a large language model released by 01.AI, released under the apache-2.0 license, with a claimed knowledge cutoff of 2023-11-02. Its weights, configuration, and tokenizer files have been cryptographically hashed and permanently attested on Ethereum (Sepolia) by Weight Registry.

Description

01.AI's open LLM series.

Metadata

Type
LLM
Issuer
01.AI
License
apache-2.0
Size
11.29 GB
Knowledge cutoff
2023-11-02
Source
https://huggingface.co/01-ai/Yi-6B
Revision
80080be87ec5a0103f643195f2d9003b8068941b
Attester
0x6a94784135e413A474E6fA28d1A36C5d180B70c9

Hugging Face stats

12,612 downloads on Hugging Face · 376 likes · pipeline: text-generation · library: transformers

transformerspytorchsafetensorsllamatext-generationeval-resultstext-generation-inferenceendpoints_compatible

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-2560x10a006c9497465b72e4791aafa7cc388f4fa00e4cc5ad6da0056324db60d9ff4
Combined SHA3-2560x9ee69f1e48b0133ee4d855c7b8dac3823798297a5e053d951f66077ff6eb0836
Combined BLAKE30xdd1bc20bbd5099b774db1d6e9290361bf704438a632dc234b92f7160fa2bb945

Per-file breakdown

Computed locally prior to attestation; the combined hash above is the canonical on-chain commitment.

Config file
config.json · 605 B
SHA-256d83b4384262d880318a406a4ab80416eeaa2265c19e96e23bec2762d055351d9
SHA3-256293ff374d8377e8f9124fd7b7094858c6da75742b92826e743b710a87352c97e
BLAKE3f633ddfdd9ade44948679ee6656076e78310b62aa95ead77f8221d6dc7d3fd62
Tokenizer file
tokenizer.json · 3.44 MB
SHA-256a13ccc285aea27f5e9a98d40e04e330b01d89db6de7af10b013f56eec8eae8a2
SHA3-2568097b0972bce87a13fe2645cdd96a04d9e6f623035d3a47c46def262c96b23d4
BLAKE3550a858fe3f36087afd60448abafb65c055d772d3b7a50e225916a398945ac38

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.