← Back to Explorer
On-Chain

Pythia-70M (2023)

Pythia-70M is a large language model released by EleutherAI, released under the apache-2.0 license, with a claimed knowledge cutoff of 2023-02-13. Its weights, configuration, and tokenizer files have been cryptographically hashed and permanently attested on Ethereum (Sepolia) by Weight Registry.

Description

Smallest member of EleutherAI's Pythia suite -- 8 model sizes from 70M to 12B, each trained on the identical Pile dataset in the identical order, with 154 intermediate checkpoints saved per model -- built as a controlled experiment platform for interpretability and training-dynamics research rather than for raw capability.

Metadata

Type
LLM
Issuer
EleutherAI
License
apache-2.0
Size
158.34 MB
Knowledge cutoff
2023-02-13
Source
https://huggingface.co/EleutherAI/pythia-70m
Revision
a39f36b100fe8a5377810d56c3f4789b9c53ac42
Attester
0x6a94784135e413A474E6fA28d1A36C5d180B70c9

Hugging Face stats

585,629 downloads on Hugging Face · 86 likes · library: gpt-neox

gpt-neoxpytorchsafetensorsgpt_neoxcausal-lmpythiaen

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-2560xf1bae9ce52a6dd29a3bc4738e081033f6bc07962b072556785a3ec914c10dde1
Combined SHA3-2560xa58c283f99ecd0aacf57e295aa2ac5f84e608eed9f7c87a59025efca122498e8
Combined BLAKE30x06d9087e869051eb261dd9c268342f9c905cb9f46c190237e48058732f022489

Per-file breakdown

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

Weights file
model.safetensors · 158.34 MB
SHA-256ebfa4e2f18696ebd83716a0d39fe2c025f2ff8483f72a83ca59c475692fc9d15
SHA3-256b373c106b4658164835575565126aa82c91d17ac00fb7f045cc779cbf41c1700
BLAKE3c200ebb9a1d50928735167782440b625ddce4b0ff1f2f2a947c40e96d7dc6e85
Config file
config.json · 567 B
SHA-256002050231a9b1ec3ac77aa6b9b3bbdc4d923f4068a7dd33b8da72a9bd6ad9a43
SHA3-25623208d6930f3a9c3b22f09188b2ef0d069b81f9ad4064430487907b66606a745
BLAKE3b75c5fb8631fa536d5aafb25c4c6df9f27f90ef07601fdcd9ef0dfd9329675f6
Tokenizer file
tokenizer.json · 2.02 MB
SHA-256c24618a1b3e6a38167beff1c72cffd126c3a66254347304b50547d12c5f25624
SHA3-256848b77cfe64befb2401c373c6b6e4c5540e7b95d79c5280f8587bf3e86eca810
BLAKE348450cf08e78d969e4b459635395e5280319b8452583ea3807fe9d01fecbfa23

Verify it yourself

curl -L -o "model.safetensors" "https://huggingface.co/EleutherAI/pythia-70m/resolve/a39f36b100fe8a5377810d56c3f4789b9c53ac42/model.safetensors"
sha256sum "model.safetensors"

Expected SHA-256: ebfa4e2f18696ebd83716a0d39fe2c025f2ff8483f72a83ca59c475692fc9d15