Abbas Foroughi

The workaround is confirmed and works in my use case.

Could you explain how to interpret the PFI calculated values? Do most important to least important is represented by positive mean values to negative or reverse?

Do you have a timeline to fix the issue? Still broken under Microsoft.ML.AutoML" 0.20.0-preview.22470.1 Microsoft.ML.TorchSharp" 0.20.0-preview.22470.1 TorchSharp 0.96.7

The roadmap should address the Model Explainability, built from bottom-up as a major milestone. I found the AutoMl.Net framework significantly improved the rapid modelling process, so I hope to see...

yes, they are not displayed.

The following enhancements are similar, perhaps can be merged to one PR and to address my requirement. Finetune #7287 Finetune #7325 https://huggingface.co/docs/transformers/v4.48.0/en/model_doc/llama2#transformers.LlamaForSequenceClassification

I agree with your recommendation. I also implemented a solution based on LlamaForCausalLM but the forword() method is not getting invoked. I am using Microsoft.ML.GenAI.LLaMA version 0.23.0-preview.25124.1, but I think...

Can you please publish a preview for Microsoft.ML.GenAI.Core package? It is not available https://pkgs.dev.azure.com/dnceng/public/_packaging/dotnet-libraries/nuget/v3/index.json The sample Microsoft.ML.GenAI.Samples/Llama/LLaMA3_1.cs is broken without it . Furthermore, the sample has hard coded weight folder...

I am getting System.IO.FileNotFoundException couldn't find model.safetensors.index.json calling at Microsoft.ML.GenAI.LLaMA.LlamaForCausalLM.FromPretrained(String modelFolder, String configName, String checkPointName, ScalarType torchDtype, String device) I can't get the example working, please explain where/what this file...

Llama3.1-8B