Update README.md
Browse files
README.md
CHANGED
@@ -14,14 +14,14 @@ tags:
|
|
14 |
- space whale
|
15 |
- 32 bit upscale
|
16 |
---
|
17 |
-
<font color=red><h3> Ultra High Remaster of the incredible: Psyonic-Cetacean-20b. </h3></font>
|
18 |
|
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.
|
25 |
|
26 |
WHY?
|
27 |
|
@@ -60,6 +60,22 @@ The mountain moved:
|
|
60 |
|
61 |
150 points better: PPL = 8.5850 +/- 0.05881 VS: BASE/ORGINAL: PPL = 8.6012 +/- 0.05900
|
62 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
<B>The bottom line here is this:</b>
|
64 |
|
65 |
Higher quality instruction following and output.
|
|
|
14 |
- space whale
|
15 |
- 32 bit upscale
|
16 |
---
|
17 |
+
<font color=red><h3> Ultra High Quality Remaster of the incredible: Psyonic-Cetacean-20b. </h3></font>
|
18 |
|
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)
|
25 |
|
26 |
WHY?
|
27 |
|
|
|
60 |
|
61 |
150 points better: PPL = 8.5850 +/- 0.05881 VS: BASE/ORGINAL: PPL = 8.6012 +/- 0.05900
|
62 |
|
63 |
+
<B>THE RESULTS ARE IN: </b>
|
64 |
+
|
65 |
+
AS per Jeb Carter, orginal creator of the model:
|
66 |
+
|
67 |
+
- instruction following has improved dramatically.
|
68 |
+
- new abilities have emerged.
|
69 |
+
- he had to REDUCE the instructions sets used because the model no longer needed as specific instructions.
|
70 |
+
- prose, nuance and depth have all improved.
|
71 |
+
- known issues with the original model have disappeared.
|
72 |
+
|
73 |
+
This is not "something for nothing" ; it is method of ensuring maximum precision at every step just before "ggufing" the model.
|
74 |
+
|
75 |
+
The methods employed only ensure precision loss is minimized or eliminated.
|
76 |
+
|
77 |
+
It is mathematical and theory sound.
|
78 |
+
|
79 |
<B>The bottom line here is this:</b>
|
80 |
|
81 |
Higher quality instruction following and output.
|