Update README.md
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ pipeline_tag: text-generation
|
|
| 18 |
|
| 19 |
Google's newest Gemma-3 model (context 32k) with "Neo Horror Imatrix" and "Maxed out" quantization to improve overall performance.
|
| 20 |
|
| 21 |
-
The "Horror Imatrix" was
|
| 22 |
|
| 23 |
5 examples provided below with prompts at IQ4XS (110 t/s on mid level card).
|
| 24 |
|
|
|
|
| 18 |
|
| 19 |
Google's newest Gemma-3 model (context 32k) with "Neo Horror Imatrix" and "Maxed out" quantization to improve overall performance.
|
| 20 |
|
| 21 |
+
The "Horror Imatrix" was built using Grand Horror 16B (at my repo). This adds a "tint" of horror to the model.
|
| 22 |
|
| 23 |
5 examples provided below with prompts at IQ4XS (110 t/s on mid level card).
|
| 24 |
|