|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
tags: |
|
- creative |
|
- story |
|
- roleplay |
|
- rp |
|
- 32 bit upscale |
|
- remastered |
|
- writing |
|
pipeline_tag: text-generation |
|
--- |
|
<h3><font color="red"> Dark Sapling V1 7B - 32k Context - Ultra Quality - 32 bit upscale.</font></h3> |
|
|
|
<img src="dark-sapling.jpg" style="width:300px; height:300px; float:right; padding:10px;"> |
|
|
|
Complete remerge, and remaster of the incredible Dark Sapling V1 7B - 32k Context from source files. |
|
|
|
Registering an impressive drop of 1000 points (lower is better) at Q4KM. |
|
|
|
This puts "Q4KM" operating at "Q6" levels, and further elevates Q6 and Q8 as well. |
|
|
|
Likewise, even Q2K (smallest quant) will operate at much higher levels than it's original source counterpart. |
|
|
|
<B>RESULTS:</b> |
|
|
|
The result is superior performance in instruction following, reasoning, depth, nuance and emotion. |
|
|
|
Reduction in prompt size, as it understands nuance better. |
|
|
|
And as a side effect more context available for output due to reduction in prompt size. |
|
|
|
Note that there will be an outsized difference between quants especially for creative and/or "no right answer" use cases. |
|
|
|
Because of this it is suggested to download the highest quant you can operate, and it's closest neighbours so to speak. |
|
|
|
IE: Q4KS, Q4KM, Q5KS as an example. |
|
|
|
Imatrix Plus versions to be uploaded at a separate repo shortly. |
|
|
|
Special thanks to "TEEZEE" the original model creator: |
|
|
|
[ https://huggingface.co/TeeZee/DarkSapling-7B-v1.0 ] |
|
|
|
NOTE: Version 1.1 and Version 2 are also remastered. |
