hierholzer
commited on
Commit
•
189bf7a
1
Parent(s):
61e42ae
Update README.md
Browse files
README.md
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
language:
|
4 |
-
- en
|
5 |
-
---
|
6 |
|
7 |
[![Hierholzer Banner](https://tvtime.us/static/images/LLAMA3.1.jpg)](#)
|
8 |
|
@@ -20,9 +20,10 @@ Models initially developed in frameworks like PyTorch can be converted to GGUF f
|
|
20 |
|
21 |
Currently, I have uploaded 2 quantized versions:
|
22 |
|
|
|
23 |
- [x] Q5_K_M ~ *Recommended*
|
24 |
-
- [x] Q8_0
|
25 |
-
- [ ]
|
26 |
|
27 |
### All Quantization Types Possible
|
28 |
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
---
|
6 |
|
7 |
[![Hierholzer Banner](https://tvtime.us/static/images/LLAMA3.1.jpg)](#)
|
8 |
|
|
|
20 |
|
21 |
Currently, I have uploaded 2 quantized versions:
|
22 |
|
23 |
+
- [x] Q4_K_M ~ *Recommended*
|
24 |
- [x] Q5_K_M ~ *Recommended*
|
25 |
+
- [x] Q8_0 ~ *NOT Recommended*
|
26 |
+
- [ ]
|
27 |
|
28 |
### All Quantization Types Possible
|
29 |
|