I am making multiple consecutive POST requests to the endpoint https://api-inference.huggingface.co/pipeline/feature-extraction/sentence-transformers/all-MiniLM-L6-v2 to embed multiple chunks of text and it works for the first 4-5 requests, but then the next POST request I make takes a very long time and in the end I get back an “Internal server error” as a response.
The request’s body is as follows:
{"inputs": texts, "options":{"wait_for_model":True}}
Why is this happening?