H34v7 - Models Merge and Collections GGUF/i1-GGUF
Collection
6 items
โข
Updated
Updated models using Dare-Ties methods. So i been tinkering for a while so i found that quantizing from F32 increase the quality slightly. And for the i-matrix i was still working on the calibration text that can enchance story perplexity.
From my experience with Q5_K_M the defiant meter is high and can be adjusted through temperature
Temperature:
In the end do your own experiment its fun.
And i think this is the best i can get from both models.
These are non i-matrix quant.
3-bit
4-bit
5-bit