Commit
•
3ffc02b
1
Parent(s):
9d2d73c
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -29,9 +29,9 @@ This model outperformed a number of other popular 70B+ models and merges in both
|
|
| 29 |
|
| 30 |
|
| 31 |
### Quantization
|
| 32 |
-
|
| 33 |
-
llama.cpp [imatrix.dat](./imatrix.dat)
|
| 34 |
-
exllamav2 [measurement.json](./measurement.json)
|
| 35 |
|
| 36 |
Will upload a few quants when bandwidth permits.
|
| 37 |
|
|
|
|
| 29 |
|
| 30 |
|
| 31 |
### Quantization
|
| 32 |
+
|
| 33 |
+
llama.cpp [imatrix.dat](./imatrix.dat)
|
| 34 |
+
exllamav2 [measurement.json](./measurement.json)
|
| 35 |
|
| 36 |
Will upload a few quants when bandwidth permits.
|
| 37 |
|