Update README.md
Browse files
README.md
CHANGED
@@ -25,6 +25,6 @@ This model takes main good features from its components, it is not censored (to
|
|
25 |
|
26 |
This model tested on core2duo E8400 with 8gb ddr2 ram, partially uploaded on 2gb gt630. It was more an experiment, but speed was bearable. On normal hardware model is FAST.
|
27 |
|
28 |
-
Of course, it is 4B after all, so don't expect 32 or 24b performance, but for it's size it is really good. For vision i used mmproj from SicariusSicariiStuff/X-Ray_Alpha
|
29 |
|
30 |
tested both q5_k_m and q8, both stable, but i reccomend to use q8 if possible.
|
|
|
25 |
|
26 |
This model tested on core2duo E8400 with 8gb ddr2 ram, partially uploaded on 2gb gt630. It was more an experiment, but speed was bearable. On normal hardware model is FAST.
|
27 |
|
28 |
+
Of course, it is 4B after all, so don't expect 32 or 24b performance, but for it's size it is really good. For vision i used mmproj from SicariusSicariiStuff/X-Ray_Alpha
|
29 |
|
30 |
tested both q5_k_m and q8, both stable, but i reccomend to use q8 if possible.
|