-
Hi there,
I am using SHAP to explain my text model, and found two explainers can be used: partition explainer and permutation explainer. They give very different results and partition explainer is mu…
-
### Problem Description
I'm currently working on a model (torch), that takes a dict of tensors as input. Thing is, each tensor has a wildly different shape, so trying to use an np array as the input …
-
Trying to follow the examples and the readme but got stuck with this error.
```
api_model = OllamaModel(model_name=model_name, api_url=api_url)
NameError: name 'OllamaModel' is not defined
```
…
-
Dear authors,
thanks for a great package.
The original python version by Lundberg offers the Boolean `approximate=True` parameter which will compute _Saabas scores_ instead of SHAP values.
Is tha…
-
Hi Jeremy,
I am re-building the ScoringEngineDemo with GenieBuidler. Here's the link to [repo](https://github.com/GenieFramework/ScoringEngineDemo.git). While restructuring the entire app I have c…
-
Multi-model endpoint workers die when the entry point imports a package installed through requirements.txt. The package is installed successfully and the endpoint is created successfully, but inferenc…
-
I trained a custom model using HF for 2-class classification. I got the prediction from the classifier as
```
[{'label': 'LABEL_0', 'score': 0.9944180250167847},
{'label': 'LABEL_1', 'score': …
-
File "C:\Users\lenovo\AppData\Local\Programs\Python\Python38\lib\site-packages\torch\autograd\__init__.py", line 202, in grad
return Variable._execution_engine.run_backward(
File "C:\Users\l…
-
Hello,
I have a question about using SHAP values if the threshold for usage (e.g., getting offered a loan based on a model score) is below the average value of default. Specifically, how do you int…
-
Hi, I'm trying to use `shap.DeepExplainer` with a PyTorch model.
The model contains a `torch.nn.Flatten` layer.
`shap.DeepExplainer.shap_values()` gives the warning `Warning: unrecognized nn.Module:…