[Python] ollama.generate raises model not found error:...

I'm trying to run a Python script that uses the ollama library to generate responses from a custom LLM model. My code attempts to call ollama.generate() using the following model name:

chosen_model = 'hf.co/mradermacher/Llama-3.2-3B-Instruct-uncensored-GGUF'



def extract_keyword(prompt):
response = ollama.generate(
model=chosen_model,
prompt=f"Identify the product/item in {prompt}. ..."
)
return response.get('response', '').strip()


I have ollama installed and running locally, and other standard models work fine.

• 
  Is 'hf.co/mradermacher/Llama-3.2-3B-Instruct-uncensored-GGUF' a valid model name for use with ollama?
  
  
• 
  Do I need to pull the model manually using ollama pull or convert it in some way?
  
  
• 
  How can I verify the availability or compatibility of a model with ollama?
  

Error

Any help to resolve this would be appreciated!

Continue reading...