🐛 Unable to call "huggingface_hub" > deprecation.py:131: FutureWarning: 'InferenceApi

[adriens]

❔ About

I'm trying to add a demo on top of huggingface mode with the following code:

%%ai huggingface_hub:TinyLlama/TinyLlama-1.1B-Chat-v1.0
Write a poem about rust language

... but I'm getting the following warning message:

/opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131:
FutureWarning: 'InferenceApi' (from 'huggingface_hub.inference_api') is deprecated
and will be removed from version '1.0'. `InferenceApi` client is deprecated in favor of
the more feature-complete `InferenceClient`.
Check out this guide to learn how to convert your script to use it: 
https://huggingface.co/docs/huggingface_hub/guides/inference#legacy-inferenceapi-client.
  warnings.warn(warning_message, FutureWarning)

without any answer.

🎯 Expected vs. current behavior

👉 I would expect to get the answer from HF, but got an empty answer:

ℹ️ Runtime

• Kaggle
• Worls well with openai/chatgpt

[welcome]

Thank you for opening your first issue in this project! Engagement like this is essential for open source projects! 🤗

If you haven't done so already, check out Jupyter's Code of Conduct. Also, please try to follow the issue template as it helps other other community members to contribute more effectively.

You can meet the other Jovyans by joining our Discourse forum. There is also an intro thread there where you can stop by and say Hi! 👋

Welcome to the Jupyter community! 🎉

[krassowski]

@adriens can you try with the latest v2.16.0? #784 migrated to the new API.

[srdas]

@adriens @krassowski I tried it with the latest release. The problem seems to be with the hosted model on huggingface.
If I use another model (mistral) it works fine but not with TinyLlama as shown here:

This seems to be a response error on the HF side. So to cross check I went to the model page and ran the model in the UI and we get this error confirming that this model cannot be used as shown below

I usually find it's best with HF to try the model out on the model page as some of the models have also become unresponsive. Hope this helps.

[adriens]

I'm giving it a try ⚡

[adriens]

🤞

[adriens]

[adriens]

So with the following code :

%%ai huggingface_hub:mistralai/Mistral-7B-v0.1
Write a poem about rust language

After many seconds, I get the following error:

[adriens]

🥳

[adriens]

I'll publish the update and tweet about it ⚡
Great job guys 🙏 😗

[adriens]

But now I'm facing a regression on chatgpt

[adriens]

• 🐛 chatgpt not available anymore in 2.16.0 : _"Cannot determine model provider from model ID openai-chatgpt."_ #803

[adriens]

💝 🎦 Seemless Huggingface Mistral inference AI call w/ Jupyter-ai

[adriens]

Tweet