MarsupialAI
commited on
Commit
•
0341198
1
Parent(s):
54f207b
Update README.md
Browse files
README.md
CHANGED
@@ -48,8 +48,12 @@ GGUFs. Then I created eight GGUFs quantized at Q4_k_m:
|
|
48 |
|
49 |
I ran PPL against all 8 quants, as well as the full fp16 and fp32 GGUFs. Results:
|
50 |
|
|
|
51 |
<in progress>
|
|
|
52 |
|
53 |
Conclusion:
|
54 |
|
|
|
55 |
<in progress>
|
|
|
|
48 |
|
49 |
I ran PPL against all 8 quants, as well as the full fp16 and fp32 GGUFs. Results:
|
50 |
|
51 |
+
````
|
52 |
<in progress>
|
53 |
+
````
|
54 |
|
55 |
Conclusion:
|
56 |
|
57 |
+
````
|
58 |
<in progress>
|
59 |
+
````
|