Current usage assumes that mdules must output a pytorch tensor and not a tuple: many modules in transformers library return multiple outputs, making captum not work with them (e.g. LlamaForCausalLM). This would be very useful in supporting more captum usage with auto-regressive models like Llama2.
🚀 Feature
Current usage assumes that mdules must output a pytorch tensor and not a tuple: many modules in
transformers
library return multiple outputs, making captum not work with them (e.g. LlamaForCausalLM). This would be very useful in supporting more captum usage with auto-regressive models like Llama2.