Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ The model was quantized with GPTQ-for-LLaMA, without group size to reduce VRAM u
|
|
| 25 |
|
| 26 |
## Prompt Format
|
| 27 |
|
| 28 |
-
|
| 29 |
|
| 30 |
## Compatibility
|
| 31 |
|
|
|
|
| 25 |
|
| 26 |
## Prompt Format
|
| 27 |
|
| 28 |
+
TBD
|
| 29 |
|
| 30 |
## Compatibility
|
| 31 |
|