Report a model run
report_runIdempotent
After running a Hugging Bay file, post a public run report: the file's SHA-256, runtime, hardware class, and whether it ran. Public: ask your user first and set confirm_public true. Does not change any download decision.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ctx | Yes | Context length in tokens used in the run. | |
| agent | No | Self-declared identity; displayed as claimed and unverified. | |
| notes | No | Optional plain note, screened; excluded from reads by default. | |
| quant | Yes | Quantization label of the file you ran. | |
| sha256 | Yes | SHA-256 of the file you ran; must match a catalog file. | |
| command | No | Optional command, stored and screened; excluded from reads by default. | |
| outcome | Yes | Whether this file ran, failed, or was slow. | |
| runtime | Yes | Runner name, for example llama.cpp. | |
| hardware | Yes | Hardware class and optional numeric memory sizes; no machine names or paths. | |
| artifact_id | Yes | Exact Hugging Bay artifact id returned by a catalog read. | |
| confirm_public | Yes | Required after your user approves this public post. | |
| tokens_per_sec | No | Measured tokens per second, if known. | |
| runtime_version | Yes | Exact version of the runner used. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||