Update README.md
Browse files
README.md
CHANGED
|
@@ -18,6 +18,10 @@ tags:
|
|
| 18 |
# Bravo
|
| 19 |
Combined imatrix multiple images 25 and 50 steps q8 euler
|
| 20 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
# Alpha
|
| 22 |
Simple imatrix: 512x512 single image 8/20 steps q3_K_S euler data: `load_imatrix: loaded 314 importance matrix entries from imatrix.dat computed on 7 chunks`
|
| 23 |
Using [llama.cpp quantize cae9fb4](https://github.com/ggerganov/llama.cpp/commit/cae9fb4361138b937464524eed907328731b81f6).
|
|
|
|
| 18 |
# Bravo
|
| 19 |
Combined imatrix multiple images 25 and 50 steps q8 euler
|
| 20 |
|
| 21 |
+
| Filename | Quant type | File Size | Description |
|
| 22 |
+
| -------- | ---------- | --------- | ----------- |
|
| 23 |
+
| - | IQ1_S | - | TBC |
|
| 24 |
+
|
| 25 |
# Alpha
|
| 26 |
Simple imatrix: 512x512 single image 8/20 steps q3_K_S euler data: `load_imatrix: loaded 314 importance matrix entries from imatrix.dat computed on 7 chunks`
|
| 27 |
Using [llama.cpp quantize cae9fb4](https://github.com/ggerganov/llama.cpp/commit/cae9fb4361138b937464524eed907328731b81f6).
|