Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,8 @@ tags:
|
|
| 19 |
This is a Floating Point 32 upscale, where all components and merges were remastered to floating point 32.
|
| 20 |
This includes all the merges (recreated with master files), and where possible subbing full FP32 models.
|
| 21 |
|
|
|
|
|
|
|
| 22 |
The goal: Carry forward maximum precision right up to the point where it is "GUFFed".
|
| 23 |
|
| 24 |
This includes F32 master file for GGUF too... at a whopping 78 GBs. (compare at 38 GBs average for 20B models)
|
|
|
|
| 19 |
This is a Floating Point 32 upscale, where all components and merges were remastered to floating point 32.
|
| 20 |
This includes all the merges (recreated with master files), and where possible subbing full FP32 models.
|
| 21 |
|
| 22 |
+
<img src="space-whale-thinking.jpg">
|
| 23 |
+
|
| 24 |
The goal: Carry forward maximum precision right up to the point where it is "GUFFed".
|
| 25 |
|
| 26 |
This includes F32 master file for GGUF too... at a whopping 78 GBs. (compare at 38 GBs average for 20B models)
|