Update README.md
Browse files
README.md
CHANGED
|
@@ -24,6 +24,8 @@ The "Horror Imatrix" was build using Grand Horror 16B. This adds a "tint" of hor
|
|
| 24 |
|
| 25 |
Examples provided below with prompts at IQ4XS (56 t/s on mid level card).
|
| 26 |
|
|
|
|
|
|
|
| 27 |
"MAXED"
|
| 28 |
|
| 29 |
This means the embed and output tensor are set at "BF16" (full precision) for all quants.
|
|
|
|
| 24 |
|
| 25 |
Examples provided below with prompts at IQ4XS (56 t/s on mid level card).
|
| 26 |
|
| 27 |
+
Context: 128k.
|
| 28 |
+
|
| 29 |
"MAXED"
|
| 30 |
|
| 31 |
This means the embed and output tensor are set at "BF16" (full precision) for all quants.
|