Hugging Face, End to End

The Hub is a host for git repositories that happen to contain neural networks, and that framing explains the rest. You will read a model card licence-first, tell the four shelves apart, run and duplicate Spaces on free hardware, keep tokens out of public code, load models and stream datasets without filling your disk, judge a leaderboard sceptically, and publish a card a stranger can act on.

1. 1The Hub is git, and that explains everything else10 minA model on the Hub is a git repository with big files stored beside it, so it has versions, history and pull requests — and if you do not pin a revision, the model under your code can change without your code changing.
2. 2Read the licence before you read the demo11 minCheck the licence family and the base model before anything else, because a fine-tune inherits its parent's terms no matter what its own card claims.
3. 3Four shelves, and picking the wrong one costs a weekend8 minModels are parts, datasets are material, Spaces are finished tools and inference is rented hardware — choose the shelf by how often the job runs and whether the data may leave your machine.
4. 4A Space is someone else's computer, already configured9 minFree CPU hardware runs one-file-at-a-time work well and cannot run image generation or fast chat, and a slow Space is usually a cold start or a shared queue rather than a fault.
5. 5Duplicate it, and the app becomes yours to change9 minDuplicating a Space gives you a private copy with no queue, but paid hardware bills for wall-clock time and does not sleep the way free hardware does — set the sleep timer before you upgrade.
6. 6A token in a public Space is a token you have given away8 minScope tokens as narrowly as the job allows, keep them in environment variables and Space secrets rather than in code, and revoke on suspicion rather than reasoning about whether a leak was seen.
7. 7Your disk fills up before your patience does11 minWeights cost parameters times bytes-per-parameter and everything downloaded lands in one shared cache, where deleting the readable filenames frees nothing because they are only links to the blobs.
8. 8Do not download the dataset9 minInspect a dataset in the viewer and stream it with `streaming=True` rather than downloading, and treat licence obligations as surviving fine-tuning until a lawyer in your country tells you otherwise.
9. 9The leaderboard is not measuring your task9 minA leaderboard narrows the field and cannot pick the winner, because contamination, selective reporting and style effects all sit between a public score and your task — thirty of your own examples decide it.
10. 10Publish it so a stranger can use it without writing to you10 minA card with a runnable snippet, a named limitation and a deliberate licence makes your work usable by strangers, and everything you would regret publishing must be decided before the first push, because copies survive deletion.