BLOOM-560m is a large language model released by BigScience, released under the bigscience-bloom-rail-1.0 license, with a claimed knowledge cutoff of 2022-07-11. Its weights, configuration, and tokenizer files have been cryptographically hashed and permanently attested on Ethereum (Sepolia) by Weight Registry.
Description
BigScience's multilingual (46-language) open LLM, the result of a large international open research collaboration, released under the usage-restricted RAIL license.
Metadata
Hugging Face stats
524,481 downloads on Hugging Face · 376 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-2560xbf7d49ff3461340a07a02bcfd3e99c9b427f7e3596a890ec6db550d5914d6984
Combined SHA3-2560xedd3b6e17e852e30d08304753611efc53f88c752a02d6b4c944cbaf3cfd01468
Combined BLAKE30x2c3946957d822b1dc982df55d4e7dcb8728d8cef2f6d6d9149c609d780454849
Per-file breakdown
Computed locally prior to attestation; the combined hash above is the canonical on-chain commitment.
Weights file
SHA-256a8702498162c95d68d2724e7f333c83d7be08de81cfc091455c38730682116d3
SHA3-2564edf34d0f76141947002a715e779d99b00287c5862bce2c31622b5531d2f8cfd
BLAKE33e6ad38f3171750ba2e5afc2069baeaadea426e0e0fd62482008d5019c2a39b0
Config file
SHA-2565a255f97efaea3c0dabef5e743d2dd969cf1f733a9c5fd6ef41a42c1aae822e9
SHA3-256c34c065c270ee4efe5920f163194602e8868a944924c93fcc7ebdb8de767a22b
BLAKE39d1bedbe61d3d854c44bcf547be7c980e09d2831f7266a32ddd6cc1862f891c2
Tokenizer file
SHA-2563fa39cd4b1500feb205bcce3b9703a4373414cafe4970e0657b413f7ddd2a9d3
SHA3-256ebbcc010e9922d7de303b218c63135ba162e0979737435d62c7e86cab379ba94
BLAKE383bf48c9cc921e0dc768275781438ea52ab1acbffa5fa44750c65ab683a676b8
Verify it yourself
curl -L -o "model.safetensors" "https://huggingface.co/bigscience/bloom-560m/resolve/ac2ae5fab2ce3f9f40dc79b5ca9f637430d24971/model.safetensors" sha256sum "model.safetensors"
Expected SHA-256: a8702498162c95d68d2724e7f333c83d7be08de81cfc091455c38730682116d3