Error occurred during model inference: 429 Client Error: Too Many Requests for url: https://api-inference.huggingface.co/models/tiiuae/falcon-7b-instruct (Request ID: X8YLkVKk4o3GBU8t7wXwX)
Model is overloaded
While using the falcon model for a personal project on chatbot, I am getting above error. can anybody help me in here. is it something which is an error from my end?
If you get that error in the middle of the process when it was working at first, it is probably simply an overuse error. Wait an hour or so, for example, and it will resolve itself. If the model does not require a token, changing the IP might be a good idea.
If you subscribe to a Pro subscription and use tokens, you can use a little more, but the exact amount has always been and always will be unknown.