Skip to content
Publishing a binding

gpt2-small-weights

607a30d

The learned numbers of GPT-2 small and its tokenizer files, pinned to one published copy.

NativeCPUmacOS arm64OfflineData

Runs on 0 of 2 nodes

that you can see

Shared

Private

  • ✕This tabBrowserCPUNeeds its handler, clay-tensor-host

See everything that runs on cloud-nbg1-1

Details · answers, reads, artifact, licence, provenance
Datafor Tensor

The learned numbers of GPT-2 small, a 2019 text-prediction model, plus the files that split text into tokens. The registry does not keep these files (the main one is about 548 MB). It records exactly which published copy is meant and the fingerprint of every file, so a runner can refuse anything that is not byte-for-byte that copy.

Runs in
With its handler
Data runs wherever its handler runs.
Form
Data files, 548 MB
Same answer every timeSame answer
Yes
Network
Never
Licence
MIT
Signed
By Clay, development keyBy Clay, dev key

The files

A handler reads these files by name. A runner refuses any file whose fingerprint differs. The registry keeps the fingerprints, not the bytes.

FileRoleSizeSHA-256
model.safetensorsweights548 MB248dfc3911…82f0f81d3a707
config.jsonconfig665 bytes0daed7749b…c56ba823bb7b4
vocab.json tokenizervocab1.0 MB196139668b…2256dbf636783
merges.txt tokenizervocab456 KB1ce1664773…be33b7726adc5
tokenizer.json tokenizertokenizer1.4 MB8414cab924…a5a9e970478a6

Where to fetch them

Repository
openai-community/gpt2
Revision
607a30d783dfa663caf39e06633721c8d4cfcd7e
Format
safetensors
Licence
MIT; redistribution allowed Hub licence tag MIT (docs/ml-m0-scope.md); the repository's licence file and the training-data terms were not read. The registry does not host the bytes.
URL pattern
https://huggingface.co/openai-community/gpt2/resolve/607a30d783dfa663caf39e06633721c8d4cfcd7e/{file}

Works with

clay-tensor-hostHandler · reads these files through Tensor.load

Exact bytes and where they came from

Upstream · huggingface.co/openai-community/gpt2
Project
https://huggingface.co/openai-community/gpt2
Version
Not recorded
Commit or revision
607a30d783dfa663caf39e06633721c8d4cfcd7e
Licence
MIT
How it was built · scripts/fetch-gpt2.sh (curl)
Toolchain
scripts/fetch-gpt2.sh (curl)
Built by
seed script (dev)
Built at
2026-11-11T06:12:18Z
Notes
builtAt is the local file time of model.safetensors. The artifact url follows the pattern scripts/fetch-gpt2.sh uses; it was not fetched again when this manifest was made. needs.memoryBytes is null: the M2 note (wishlist W32) says the host holds the whole file and peaks near 1.1 GB for GPT-2, but that was not measured for this entry.
Memory
Not measured
CPU
Not measured
Source path
.tools/models/gpt2/model.safetensors
Format
file
  1. scripts/fetch-gpt2.sh downloads each file from the pinned revision into .tools/models/gpt2 and refuses any sha256 that differs from packages/tensor-host/models/gpt2.json.
  2. This manifest was built from those local files; the sha256 values equal models/gpt2.json.
Signatures · 1, development key

Checked when this page was built, against the trust set.

  • c5878029baeb4574 Clay, development key: valid (ok)
Manifest id
e985e378761acf4cc3d8f074f5634b6924b754b5668f15d95135a6f055423d75
Status
ok
Loading it from a runner · checkLoadable, with the code

Fetch /v1/manifests/e985e378761acf4cc3d8f074f5634b6924b754b5668f15d95135a6f055423d75.json, get the artifact bytes by hash (and the other pinned files), then call checkLoadable(manifest, bytes, policy, companionFiles). It checks the signature against the trusted keys, the revocation list, the fingerprints and sizes, and the policy’s allowed forms and determinism classes, and returns a reason when it refuses. How a runner loads a binding