openai-community/gpt2
text-generation · 0.14B parameters · 1.0 GiB of weights at revision 607a30d7.
Runs on a single GPU when the source verified it.
Did this card launch? The count is real — it comes from launches the kit recorded against this path, not from a widget anywhere.
| weight path | openai-community/gpt2 |
|---|---|
| revision | 607a30d783dfa663caf39e06633721c8d4cfcd7e |
| license | mit |
| gated | no |
| parameters | 0.14B |
| weight bytes | 1.0 GiB |
| modality | text-generation |
| HF downloads | 27.8M at capture |
| last modified | 2024-02-19T10:57:45.000Z |
The checkpoints.
Every servable variant in or beside the repo. resident_gib is what lands in
VRAM after load; host_gib is what stays on the host and never touches the
card.
| name | format | location | resident | host tier | gated |
|---|---|---|---|---|---|
root | bf16 | repo root | 1.0 GiB | — | no |
root — 2 weight file(s)
No published launch.
Neither vLLM nor SGLang publishes a launch for this path at capture. The card says so rather than composing a command that has never run: that is what the gap list below is for.
Every floor a box must clear.
A launch that fails on the third requirement wasted the first two. These are the requirements, as data — the fit gate reads them instead of a paragraph.
| GPU models | none validated |
|---|---|
| architectures | — |
| min GPUs | 1 |
| TP rule | no published TP; single-GPU or unstated |
| min VRAM / GPU | — |
| min total VRAM | — |
| min disk | 51 GiB |
| min host RAM | — |
| interconnect | not required |
| CUDA min | — |
| driver min | — |
| context tokens | — |
The 3 things this card could not answer.
First-class, not swallowed. Every entry is a field a source did not answer — which makes it a launch nobody has done, and therefore a unit of work rather than a defect.
envs.vllm no published vLLM recipe for this repo envs.sglang no SGLang cookbook page matched this repo hardware.validated no source marks a hardware family verified The file.
The card is a YAML document with a published JSON Schema. View it, download it, diff it
against the next capture — and point one at it.
download
Same bytes the collector wrote. The JSON is the same card, for a machine that would rather not parse YAML.
with one
one launch --card openai-community/gpt2/launch-card.yaml one follows the argv above, checks the floors before the paid clock, and on
a failure changes exactly one field and retries — recording every attempt against this
path.
Where every field came from.
The card is assembled, not authored. These are the sources, so a reader can check the claim rather than trust it.
| source | url |
|---|---|
| hf-api | https://huggingface.co/api/models/openai-community/gpt2 |
Captured 2026-10-31T17:28:03Z by hf-api + vllm-recipes + sglang-cookbook.
Schema onefrontier.launch-card/v1.