Model does not exist

[tatihden]

I have completely built my space. The status says running. However, every time I try a chat, I get the following error codes in the log;

huggingface_hub.errors.HfHubHTTPError: 404 Client Error: Not Found for url: https://huggingface.co/proxy/api-inference.huggingface.co/models/hf://tatihden/gemma_mental_health_2b_en (Request ID: _X6BQvk9F_8zeSSxjuudQ)

Model hf://tatihden/gemma_mental_health_2b_en does not exist

Please help. Thanks

[John6666]

The cause seems to be in the model and HF server, not the program. It seems that using Keras models with InferenceClient is not supported.
I think it will work if you use a model that is not in Keras format or write a program for Keras.

tatihden/gemma_mental_health_2b_it_en · Hugging Face

Inference API (serverless) does not yet support keras-hub models for this pipeline type.

[tatihden]

Thanks for this response. I really appreciate it.

Yahoo Mail: Search, Organize, Conquer

[CM191919191992]

What happened today when some HuggingChat models never existed! HELP

[John6666]

I think the Inference API is buggy across the whole Hugging Face at the moment. Hugging Chat was working until about an hour ago, but now it’s not.

HF Inference API last few minutes returns the same 404 exception to all models

I’m getting this message in my log: huggingface_hub.errors.HfHubHTTPError: 503 Server Error: Service Temporarily Unavailable for url: https://huggingface.co/proxy/router.huggingface.co/hf-inference/models/google/gemma-2-2b-it same goes for gemma-2-9b-it. 2b worked yesterday. If I follow the link, I get: 404 Sorry, we can’t find the page you are looking for.

Edit:
503 now.

[John6666]

It’s not counted as downtime, and it’s probably not actually down, but it’s running in an error state.

Hugging Face status