|
pulsatrix 1.1.0
|
A sampled sequence and how it was produced. More...
#include <masked_diffusion.hpp>
Public Attributes | |
| std::vector< int64_t > | tokens |
| The final sequence: no masked position remains. | |
| std::vector< MaskedDiffusionStep > | steps |
| Every step that filled something (under Remasking, every step), in order. Each step's input is the previous step's input with the previous writes and re-masks applied. | |
| std::vector< int64_t > | last_write_step |
For each position, the index into steps of the step that last wrote it, or -1 for a position that wasn't masked in the input (a prompt token). Under Confidence and Ancestral a position's last write is also its only one; under Remasking a position can be written, masked again and rewritten. | |
A sampled sequence and how it was produced.
| std::vector<int64_t> pulsatrix::MaskedDiffusionResult::last_write_step |
For each position, the index into steps of the step that last wrote it, or -1 for a position that wasn't masked in the input (a prompt token). Under Confidence and Ancestral a position's last write is also its only one; under Remasking a position can be written, masked again and rewritten.
| std::vector<MaskedDiffusionStep> pulsatrix::MaskedDiffusionResult::steps |
Every step that filled something (under Remasking, every step), in order. Each step's input is the previous step's input with the previous writes and re-masks applied.
| std::vector<int64_t> pulsatrix::MaskedDiffusionResult::tokens |
The final sequence: no masked position remains.