MarsupialAI
commited on
Commit
•
9e393d5
1
Parent(s):
c86265d
Update README.md
Browse files
README.md
CHANGED
@@ -46,7 +46,8 @@ GGUFs. Then I created eight GGUFs quantized at Q4_k_m:
|
|
46 |
- fp32 GGUF, no imatrix
|
47 |
- fp16 GGUF, no imatrix
|
48 |
|
49 |
-
I ran PPL against all 8 quants, as well as the full fp16 and fp32 GGUFs.
|
|
|
50 |
|
51 |
````
|
52 |
<in progress>
|
@@ -57,3 +58,4 @@ Conclusion:
|
|
57 |
````
|
58 |
<in progress>
|
59 |
````
|
|
|
|
46 |
- fp32 GGUF, no imatrix
|
47 |
- fp16 GGUF, no imatrix
|
48 |
|
49 |
+
I ran PPL against all 8 quants, as well as the full fp16 and fp32 GGUFs. All iMatrices were created using Kalomaze's
|
50 |
+
groups_merged.txt. All PPL calcs were run using wiki.short.raw. Results:
|
51 |
|
52 |
````
|
53 |
<in progress>
|
|
|
58 |
````
|
59 |
<in progress>
|
60 |
````
|
61 |
+
|