Commit
•
65297bf
1
Parent(s):
abcdffb
"Update README.md"
Browse files
README.md
CHANGED
|
@@ -51,7 +51,7 @@ The core project making use of the ggml library is the [llama.cpp](https://githu
|
|
| 51 |
|
| 52 |
There is a bunch of quantized files available. How to choose the best for you:
|
| 53 |
|
| 54 |
-
#
|
| 55 |
|
| 56 |
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
|
| 57 |
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
|
|
@@ -65,6 +65,7 @@ With a Q6_K you should find it really hard to find a quality difference to the o
|
|
| 65 |
|
| 66 |
|
| 67 |
|
|
|
|
| 68 |
# Original Model Card:
|
| 69 |
# 🚀 Falcon-7B
|
| 70 |
|
|
@@ -295,6 +296,7 @@ Falcon-7B is made available under the Apache 2.0 license.
|
|
| 295 | |
| 296 |
|
| 297 |
***End of original Model File***
|
|
|
|
| 298 |
|
| 299 |
|
| 300 |
## Please consider to support my work
|
|
|
|
| 51 |
|
| 52 |
There is a bunch of quantized files available. How to choose the best for you:
|
| 53 |
|
| 54 |
+
# Legacy quants
|
| 55 |
|
| 56 |
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are `legacy` quantization types.
|
| 57 |
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
|
|
|
|
| 65 |
|
| 66 |
|
| 67 |
|
| 68 |
+
---
|
| 69 |
# Original Model Card:
|
| 70 |
# 🚀 Falcon-7B
|
| 71 |
|
|
|
|
| 296 | |
| 297 |
|
| 298 |
***End of original Model File***
|
| 299 |
+
---
|
| 300 |
|
| 301 |
|
| 302 |
## Please consider to support my work
|