<img src="https://w.forfun.com/fetch/cb/cba2205390e517bea1ea60ca0b491af4.jpeg" style="width: 70%; min-width: 300px; display: block; margin: auto;">
<br>An experimental merging of Several Models using two various methods, Ties-Merge and BlockMerge_Gradient
GGUF FILES HERE <br>Included Quants: Q4_K_S, Q5_K_M, Q6_K
Stheno-1.2-L2-13B - Merged at Heavier Densities, Final Gradient Merge uses unique ratios.
Stheno-Inverted-1.2-L2-13B - Merged at Heavier Densities, Final Gradient Merge uses unique ratios. Inverted Model Positions
Stheno-1.3-L2-13B - Merged at Heavier Densities, Final Gradient Merge uses unique ratios + SLERP implementation thanks to @Vali
Stheno-L2-13B <br>Stheno-Inverted-L2-13B <br>Stheno-P1-L2-13B --FP16 Private-- <br>Stheno-P2-L2-13B --FP16 Private--
Refer to original cards for more info
Most formats could work, but my tests have all been done in Alpaca format and it works well.
### Instruction:
Your instruction or question here.
For roleplay purposes, I suggest the following - Write <CHAR NAME>'s next reply in a chat between <YOUR NAME> and <CHAR NAME>. Write a single reply only.
### Response:
Once Again, thanks to Chargoddard for his amazing and simple ties-merge script, and Gryphe for their great BlockMerge_Gradient script. Thanks to the original model creators too!
Art by wada_kazu / わだかず (pixiv page private?)