← Back to Explorer
Pending

gemma-7b (2024)

gemma-7b is a large language model released by Google, released under the Gemma license license, with a claimed knowledge cutoff of 2024-02-21. Its weights, configuration, and tokenizer files have been cryptographically hashed and are queued for on-chain attestation by Weight Registry.

Description

Base (non-instruct) Gemma 7B checkpoint, part of Google's first Gemma generation.

Metadata

Type
LLM
Issuer
Google
License
Gemma license
Size
15.90 GB
Knowledge cutoff
2024-02-21
Source
https://huggingface.co/google/gemma-7b
Revision
ff6768d9368919a1f025a54f9f5aa0ee591730bb

Hugging Face stats

24,452 downloads on Hugging Face · 3,444 likes · pipeline: text-generation · library: transformers

transformerssafetensorsggufgemmatext-generationeval-resultstext-generation-inferenceendpoints_compatible

Weight Hashes

Weights file
4 shards (Merkle root) · 15.90 GB
SHA-2567e4fdc0f9546390d22f3514ce3191f474421c542b1ce8dba5010f583a47b2d6c
SHA3-256271679d3757b896697954556b0bb6613074bcea1a6a8c30b04ad95a48505e3fb
BLAKE354a8bb2eb4f7283c50c2f180f403aad944afd552dbeaa37b6cdc7fe07dd3d53f
Config file
config.json · 629 B
SHA-256681aa5004e71e55e5d6344f697ebefbf16b376297df890b075121dc5b89b93fb
SHA3-25630e956415509767fcf47b6c7c7e7e48ca23cd801ce70e9a27394773b2077aa58
BLAKE32bce3bf019f18c493856e575dc8450fb6caf6186a8ccc6637644f9d87b303c89
Tokenizer file
tokenizer.json · 16.71 MB
SHA-256c15eb04bc5ad609fb26533e8525302c5640a945e5f67f65b7c849900acda7d99
SHA3-2566c4d860d7fb19bd061f35b3f718b27a382ca39d2e09234a819b8cb9dffd83e85
BLAKE334dda6e9d6b0d371c84d6b9ccf89b45a94812374c33d976d6ef230ff5f86f654

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.