AI Agent Course

Hi everyone,

I’m currently running this notebook:
unit2/smolagents/code_agents.ipynb · agents-course/notebooks at main, but it’s returning an error.

So far, I’ve been unable to successfully run most of the examples in the course. I’m unsure if this is due to an issue with my account settings.

Do you have any suggestions?

Error in generating model output:
Provider ‘nscale’ not supported. Available values: ‘auto’ or any provider from [‘black-forest-labs’, ‘cerebras’,
‘cohere’, ‘fal-ai’, ‘fireworks-ai’, ‘hf-inference’, ‘hyperbolic’, ‘nebius’, ‘novita’, ‘openai’, ‘replicate’,
‘sambanova’, ‘together’].Passing ‘auto’ (default value) will automatically select the first provider available for
the model, sorted by the user’s order in Hugging Face – The AI community building the future..
[Step 1: Duration 0.01 seconds]

ValueError Traceback (most recent call last)
/usr/local/lib/python3.11/dist-packages/smolagents/agents.py in _step_stream(self, memory_step)
1495 else:
→ 1496 chat_message: ChatMessage = self.model.generate(
1497 input_messages,

8 frames
ValueError: Provider ‘nscale’ not supported. Available values: ‘auto’ or any provider from [‘black-forest-labs’, ‘cerebras’, ‘cohere’, ‘fal-ai’, ‘fireworks-ai’, ‘hf-inference’, ‘hyperbolic’, ‘nebius’, ‘novita’, ‘openai’, ‘replicate’, ‘sambanova’, ‘together’].Passing ‘auto’ (default value) will automatically select the first provider available for the model, sorted by the user’s order in Hugging Face – The AI community building the future..

The above exception was the direct cause of the following exception:

AgentGenerationError Traceback (most recent call last)
/usr/local/lib/python3.11/dist-packages/smolagents/agents.py in _step_stream(self, memory_step)
1516 memory_step.model_output = output_text
1517 except Exception as e:
→ 1518 raise AgentGenerationError(f"Error in generating model output:\n{e}", self.logger) from e
1519
1520 ### Parse output ###

AgentGenerationError: Error in generating model output:
Provider ‘nscale’ not supported. Available values: ‘auto’ or any provider from [‘black-forest-labs’, ‘cerebras’, ‘cohere’, ‘fal-ai’, ‘fireworks-ai’, ‘hf-inference’, ‘hyperbolic’, ‘nebius’, ‘novita’, ‘openai’, ‘replicate’, ‘sambanova’, ‘together’].Passing ‘auto’ (default value) will automatically select the first provider available for the model, sorted by the user’s order in Hugging Face – The AI community building the future..

1 Like

You are trying to use a provider called NScale. The backend doesn’t support that provider for that Model. Switch to auto and Huggingface will pick the first provider for you for that model.
Alternatively, you can go research the model on Huggingface and see what providers are available for that model and pass that arguement accordingly.

Hope that helps :slight_smile:

2 Likes

This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.