Hi there,
Hope someone can help on this subject.
I am going through and trying to use an Hugging Face model to be used creating and then using semantic functions.
I am trying to reproduce the lab in my Google Colab using a T4 GPU.
First, I had to install a couple of requirements but everything went fine.
I was able to upload this model: “microsoft/phi-1_5” and other relatively small models, because of memory restrictions.
I was able to create a kernel, all fine until that point.
I was able to create a semantic function.
I was able to add context elements to the function.
\Then when trying to use the function with:
“result = await kernel.run_async(shift_domain_function, input_context=my_context)”
I got some warnings:
"/usr/local/lib/python3.10/dist-packages/transformers/generation/configuration_utils.py:362: UserWarning: do_sample
is set to False
. However, temperature
is set to 0.1
– this flag is only used in sample-based generation modes. You should set do_sample=True
or unset temperature
. This was detected when initializing the generation config instance, which means the corresponding file may hold incorrect parameterization and should be fixed.
warnings.warn(
/usr/local/lib/python3.10/dist-packages/transformers/generation/configuration_utils.py:367: UserWarning: do_sample
is set to False
. However, top_p
is set to 0.5
– this flag is only used in sample-based generation modes. You should set do_sample=True
or unset top_p
. This was detected when initializing the generation config instance, which means the corresponding file may hold incorrect parameterization and should be fixed.
warnings.warn("
And the result display the following error:
“Error: (‘Hugging Face completion failed’, TypeError(”‘NoneType’ object is not callable"), None)"
I have tried to find out this by myself with no luck. Hope someone can help!
Thanks
Mario