Commit
•
6230c23
1
Parent(s):
f3e09a1
"Update README.md"
Browse files
README.md
CHANGED
|
@@ -54,7 +54,7 @@ The core project making use of the ggml library is the [llama.cpp](https://githu
|
|
| 54 |
|
| 55 |
There is a bunch of quantized files available. How to choose the best for you:
|
| 56 |
|
| 57 |
-
#
|
| 58 |
|
| 59 |
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
|
| 60 |
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
|
|
@@ -68,10 +68,12 @@ With a Q6_K you should find it really hard to find a quality difference to the o
|
|
| 68 |
|
| 69 |
|
| 70 |
|
|
|
|
| 71 |
# Original Model Card:
|
| 72 |
|
| 73 |
|
| 74 |
***End of original Model File***
|
|
|
|
| 75 |
|
| 76 |
|
| 77 |
## Please consider to support my work
|
|
|
|
| 54 |
|
| 55 |
There is a bunch of quantized files available. How to choose the best for you:
|
| 56 |
|
| 57 |
+
# Legacy quants
|
| 58 |
|
| 59 |
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
|
| 60 |
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
|
|
|
|
| 68 |
|
| 69 |
|
| 70 |
|
| 71 |
+
---
|
| 72 |
# Original Model Card:
|
| 73 |
|
| 74 |
|
| 75 |
***End of original Model File***
|
| 76 |
+
---
|
| 77 |
|
| 78 |
|
| 79 |
## Please consider to support my work
|