Unknown error in model inference API

[ivelin]

Hub team,

My model appears to load fine and the API widget accepts queries, but the result is unknown error. Any clues how to get to the root cause?

ivelin/donut-refexp-combined-v1 · Hugging Face

Thank you!

I see several other people reported similar issues in the past without clear response:

Unexpected appeared "unknown error" in Inference API

Hello! I uploaded my first model to the Huggingface HUB Mraleksa/fine-tune-distilbert-exitru · Hugging Face, and was immediately able to use the Inference API. But a few hours later, an “unknown error” was received, despite the API status being displayed as “This model is now loaded and running on the Inference API.” Can someone tell me how it happened?

Feature extraction using Inference API error

I had this same issue. It appears in the model hub some of the sentence-transformer API endpoints are set up for sentence similarity while others are set up for feature extraction. Passing the query as you have there to a sentence similarity endpoint results in an error. Try using a different model with a feature extraction endpoint like: Craig/paraphrase-MiniLM-L6-v2 or julien-c/distilbert-feature-extraction

Inference API Issues

Hello, My team have currently been using the Inference API under the Lab pricing model specifically to use the philschmid/bart-large-cnn-samsum model to summarise conversations. The API and model were working fine up until a few days ago when we started receiving the following error every-time we try and call the model: error_message 'unknown error' exception HuggingFaceModelNotAvailableYetError('unknown error') response <Response [500]> response_content { error: 'unknown error', warnings: [ "…