Endpoint cannot be created if model repo name is >60 characters

[bdzyubak]

Describe the bug

We fine tune models and store them on HuggingFace hub. The model names are built from datasetid__experiment name such as:
Company/client1_fielddata_[date]__favoritemodel_finetuned_300epochs

We have noticed random-appearing crashes when trying to create the endpoint, and narrowed it down to the model name being too long. The issue is twofold:

1. The error message is unclear and does not lead you to recreate a model under a different name.
2. The name restriction of 70 (60?) characters together with namespace is restricting. Having long descriptive model names is helpful during the experimentation phase.

Reproduction

endpoint = create_inference_endpoint(
name='client1_fielddata_favoritemodel_finetuned',
repository='Company/client1_fielddata_[date]__favoritemodel_finetuned_300epochs,
framework="pytorch",
task="custom",
accelerator="gpu",
vendor=vendor,
region=region,
type="protected",
instance_size="x1",
instance_type="nvidia-l4",
custom_image={
"health_route": "/health",
"env": env_vars,
"url": VLLM_HF_IMAGE_URL,
},
token=os.getenv("HF_TOKEN"),
namespace="Company"
)

Logs

Traceback (most recent call last):
  File "/Applications/PyCharm.app/Contents/plugins/python/helpers-pro/pydevd_asyncio/pydevd_asyncio_utils.py", line 117, in _exec_async_code
    result = func()
             ^^^^^^
  File "<input>", line 1, in <module>
  File "/Users/bdzyubak/Library/Caches/pypoetry/virtualenvs/vlm-finetuning-X38kV7cE-py3.11/lib/python3.11/site-packages/huggingface_hub/hf_api.py", line 7264, in create_inference_endpoint
    hf_raise_for_status(response)
  File "/Users/bdzyubak/Library/Caches/pypoetry/virtualenvs/vlm-finetuning-X38kV7cE-py3.11/lib/python3.11/site-packages/huggingface_hub/utils/_errors.py", line 358, in hf_raise_for_status
    raise BadRequestError(message, response=response) from e
huggingface_hub.utils._errors.BadRequestError:  (Request ID: m4c7P7)
Bad request:
Bad Request: Invalid name

System info

- huggingface_hub version: 0.24.6
- Platform: macOS-14.6.1-arm64-arm-64bit
- Python version: 3.12.4
- Running in iPython ?: No
- Running in notebook ?: No
- Running in Google Colab ?: No
- Token path ?: /Users/bdzyubak/.cache/huggingface/token
- Has saved token ?: True
- Who am I ?: bdzyubak
- Configured git credential helpers: osxkeychain
- FastAI: N/A
- Tensorflow: N/A
- Torch: 2.4.0
- Jinja2: 3.1.4
- Graphviz: N/A
- keras: N/A
- Pydot: N/A
- Pillow: 10.4.0
- hf_transfer: N/A
- gradio: 4.41.0
- tensorboard: N/A
- numpy: 1.26.4
- pydantic: 2.8.2
- aiohttp: 3.10.5
- ENDPOINT: https://huggingface.co
- HF_HUB_CACHE: /Users/bdzyubak/.cache/huggingface/hub
- HF_ASSETS_CACHE: /Users/bdzyubak/.cache/huggingface/assets
- HF_TOKEN_PATH: /Users/bdzyubak/.cache/huggingface/token
- HF_HUB_OFFLINE: False
- HF_HUB_DISABLE_TELEMETRY: False
- HF_HUB_DISABLE_PROGRESS_BARS: None
- HF_HUB_DISABLE_SYMLINKS_WARNING: False
- HF_HUB_DISABLE_EXPERIMENTAL_WARNING: False
- HF_HUB_DISABLE_IMPLICIT_TOKEN: False
- HF_HUB_ENABLE_HF_TRANSFER: False
- HF_HUB_ETAG_TIMEOUT: 10
- HF_HUB_DOWNLOAD_TIMEOUT: 10

[Wauplin]

Hi @bdzyubak, thanks raising the question. I'll forward your issue internally.