# What is 'model is currently loading;'
**URL:**
**Author:**  [@Doogie](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FDoogie)%5C
**Post date:** [January 20, 2022, 3:24am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-is-model-is-currently-loading%2F13917%2F1 "2022-01-20T03:24:12Z")
Hi.
I’m a beginner at NLP.
I’m going to summarize sentences using T5 model’s information API.
The model is currently loading keeps popping up and does not proceed.
Can you tell me what this error is?
also
I want to summarize more than 5,000 characters into 1,000 to 2,000 characters.
How should I write the parameters?
---
**Author:**  [@merve](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fmerve)%5C
**Post date:** [January 20, 2022, 1:23pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-is-model-is-currently-loading%2F13917%2F2 "2022-01-20T13:23:26Z")
@Doogie
Hello 🤗
Inference API loads models on demand, so if it’s your first time using it in a while it will load the model first, then you can try to send the request again in couple of seconds.
---
**Author:**  [@osanseviero](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fosanseviero)%5C
**Post date:** [January 20, 2022, 5:30pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-is-model-is-currently-loading%2F13917%2F3 "2022-01-20T17:30:56Z")
As per [Detailed parameters — Api inference documentation](/static-proxy?url=https%3A%2F%2Fapi-inference.huggingface.co%2Fdocs%2Fpython%2Fhtml%2Fdetailed_parameters.html)%2C you can use the `wait_for_model` option to wait for the response instead of having to do multiple requests.
---
**Author:**  [@Doogie](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FDoogie)%5C
**Post date:** [January 21, 2022, 1:41am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-is-model-is-currently-loading%2F13917%2F4 "2022-01-21T01:41:37Z")
Thank you for answering.
I hope this model is always ready.
What should I do to do that?
Model should always show me response immediately.
Can i pinned the model?
---
**Author:**  [@Doogie](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FDoogie)%5C
**Post date:** [January 21, 2022, 1:45am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-is-model-is-currently-loading%2F13917%2F5 "2022-01-21T01:45:58Z")
Thank you for answering!
i hope this model is always ready
wait\_for\_model parameters means ready to model?
---
**Author:**  [@osanseviero](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fosanseviero)%5C
**Post date:** [January 21, 2022, 10:48am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-is-model-is-currently-loading%2F13917%2F6 "2022-01-21T10:48:02Z")
`wait_for_model` is documented in the link shared above.
If false, you will get a 503 when it’s loading. If true, your process will hang waiting for the response, which might take a bit while the model is loading. You can pin models for instant loading (see [Hugging Face – Pricing](https://huggingface.co/pricing))
---
**Author:**  [@deseipel](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdeseipel)%5C
**Post date:** [October 3, 2022, 1:22am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-is-model-is-currently-loading%2F13917%2F7 "2022-10-03T01:22:42Z")
I get a message that wait\_for\_model is no longer valid
{‘inputs’: {‘past\_user\_inputs’: , ‘generated\_responses’: , ‘text’: ‘yo’}, ‘parameters’: {‘min\_length’: 1, ‘max\_length’: 500, ‘repetition\_penalty’: 50.0, ‘temperature’: 50.0, ‘use\_cache’: True, ‘wait\_for\_model’: True}}
{“error”: “The following `model_kwargs` are not used by the model: [‘wait\_for\_model’] (note: typos in the generate arguments will also show up in this list)”}
---
**Author:**  [@GillesM](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FGillesM)%5C
**Post date:** [April 3, 2023, 2:28pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-is-model-is-currently-loading%2F13917%2F9 "2023-04-03T14:28:13Z")
Hi. With “togethercomputer/GPT-NeoXT-Chat-Base-20B” I’m using the “wait\_for\_model” parameter set to true, but I still have the “Model is currently loading”. Is it because the model is too big ?
---
**Author:**  [@anon84609851](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fanon84609851)%5C
**Post date:** [May 18, 2023, 9:01am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-is-model-is-currently-loading%2F13917%2F10 "2023-05-18T09:01:58Z")
I’ve set the `wait_for_model` parameter to True in the payload in the same way as @deseipel and it doesn’t work for me either. I don’t get a specific error about the request, I just get the usual 503 error in response: “Model is currently loading”.
---
**Author:**  [@anon84609851](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fanon84609851)%5C
**Post date:** [May 18, 2023, 9:51am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-is-model-is-currently-loading%2F13917%2F11 "2023-05-18T09:51:43Z")
I have finally managed to use the flag - the “parameters” dictionary actually needs to be called the “options” dictionary according to the documentation [https://huggingface.co/docs/api-inference/detailed\_parameters](https://huggingface.co/docs/api-inference/detailed_parameters)
However, after overcoming that error and duly waiting for a response, I waited, and got a 504 error instead: Gateway Timeout. Is HF down today?
---
**Author:**  [@richardantao](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Frichardantao)%5C
**Post date:** [January 31, 2024, 2:25am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fwhat-is-model-is-currently-loading%2F13917%2F12 "2024-01-31T02:25:25Z")
It’s not that the ‘parameters’ dictionary needs to be called ‘options’; rather, there is a separate argument from ‘parameters’ called ‘options’ that specifically takes the ‘use\_cache’ and ‘wait\_for\_model’ keys in the dict.