|
pulsatrix 1.1.0
|
The two explanations of the same prediction, and their difference. More...
#include <fine_tune_diff.hpp>

Public Attributes | |
| Tensor | tuned |
The fine-tuned model's input relevance, as its propagate_relevance() returns it ((N, L) per token for a language model). | |
| Tensor | base |
| The base model's, for the same class at the same position. | |
| Tensor | difference |
| tuned - base. | |
| std::vector< int64_t > | classes |
| The class explained for each sample. | |
| std::vector< double > | tuned_scores |
| Each model's output at that class, per sample: the relevance each one distributes. | |
| std::vector< double > | base_scores |
The two explanations of the same prediction, and their difference.
| Tensor pulsatrix::RelevanceDiff::base |
The base model's, for the same class at the same position.
| std::vector<double> pulsatrix::RelevanceDiff::base_scores |
| std::vector<int64_t> pulsatrix::RelevanceDiff::classes |
The class explained for each sample.
| Tensor pulsatrix::RelevanceDiff::difference |
tuned - base.
| Tensor pulsatrix::RelevanceDiff::tuned |
The fine-tuned model's input relevance, as its propagate_relevance() returns it ((N, L) per token for a language model).
| std::vector<double> pulsatrix::RelevanceDiff::tuned_scores |
Each model's output at that class, per sample: the relevance each one distributes.