Update README.md
Browse files
README.md
CHANGED
|
@@ -38,6 +38,8 @@ Model | F16 | Q4_0 | Q4_1 | Q4_2 | Q4_3 | Q5_0 | Q5_1 | Q8_0
|
|
| 38 |
q5_1 or 5_0 are the latest and most performant implementations. The former is slightly more accurate at the cost of a bit of performance. Most users should use one of the two.
|
| 39 |
If you encounter any kind of compatibility issues, you might want to try the older q4_x
|
| 40 |
|
|
|
|
|
|
|
| 41 |
---
|
| 42 |
|
| 43 |
# Vicuna Model Card
|
|
|
|
| 38 |
q5_1 or 5_0 are the latest and most performant implementations. The former is slightly more accurate at the cost of a bit of performance. Most users should use one of the two.
|
| 39 |
If you encounter any kind of compatibility issues, you might want to try the older q4_x
|
| 40 |
|
| 41 |
+
**NOTE: q4_3 is EOL - avoid using.**
|
| 42 |
+
|
| 43 |
---
|
| 44 |
|
| 45 |
# Vicuna Model Card
|