Commit
•
bde709a
1
Parent(s):
1386567
Update README.md
Browse files
README.md
CHANGED
@@ -52,4 +52,4 @@ Extract the two .zip files directly into the llama.cpp folder you just git clone
|
|
52 |
## Windows command prompt - Quantize the fp16 model to q5_k_m:
|
53 |
* D:\llama.cpp>quantize.exe D:\Mixtral\Mixtral-8x7B-Instruct-v0.1.fp16.bin D:\Mixtral\Mixtral-8x7B-Instruct-v0.1.q5_k_m.gguf q5_k_m
|
54 |
|
55 |
-
That's it
|
|
|
52 |
## Windows command prompt - Quantize the fp16 model to q5_k_m:
|
53 |
* D:\llama.cpp>quantize.exe D:\Mixtral\Mixtral-8x7B-Instruct-v0.1.fp16.bin D:\Mixtral\Mixtral-8x7B-Instruct-v0.1.q5_k_m.gguf q5_k_m
|
54 |
|
55 |
+
That's it!
|