Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ All credits belong to the respective creators.
|
|
| 15 |
|
| 16 |
`Base⇢ GGUF(F16)⇢ GGUF(Quants)`
|
| 17 |
|
| 18 |
-
Using [llama.cpp](https://github.com/ggerganov/llama.cpp/)-b2222. **
|
| 19 |
|
| 20 |
# Original model information:
|
| 21 |
|
|
|
|
| 15 |
|
| 16 |
`Base⇢ GGUF(F16)⇢ GGUF(Quants)`
|
| 17 |
|
| 18 |
+
Using [llama.cpp](https://github.com/ggerganov/llama.cpp/)-b2222. **For --imatrix, included reference `imatrix.dat` was used.**
|
| 19 |
|
| 20 |
# Original model information:
|
| 21 |
|