parameters guide
samplers guide
model generation
role play settings
quant selection
arm quants
iq quants vs q quants
optimal model setting
gibberish fixes
coherence
instructing following
quality generation
chat settings
quality settings
llamacpp server
llamacpp
lmstudio
sillytavern
koboldcpp
backyard
ollama
model generation steering
steering
model generation fixes
text generation webui
ggufs
exl2
full precision
quants
imatrix
neo imatrix
Update README.md
Browse files
README.md
CHANGED
@@ -368,7 +368,7 @@ F16 is full precision, just in GGUF format.
|
|
368 |
|
369 |
CPU ONLY CONSIDERATIONS:
|
370 |
|
371 |
-
This section DOES NOT apply to most "Macs" because of the difference in O/S Memory, Vram and motherboard VS other frameworks
|
372 |
|
373 |
Running quants on CPU will be a lot slower than running them on a video card(s).
|
374 |
|
@@ -799,9 +799,9 @@ If not set to 1, select only tokens that are at least this much more likely to a
|
|
799 |
|
800 |
<B> XTC</B>
|
801 |
|
802 |
-
xtc-probability
|
803 |
|
804 |
-
|
805 |
|
806 |
Probability that the removal will actually happen. 0 disables the sampler. 1 makes it always happen.
|
807 |
|
|
|
368 |
|
369 |
CPU ONLY CONSIDERATIONS:
|
370 |
|
371 |
+
This section DOES NOT apply to most "Macs" because of the difference in O/S Memory, Vram and motherboard VS other frameworks.
|
372 |
|
373 |
Running quants on CPU will be a lot slower than running them on a video card(s).
|
374 |
|
|
|
799 |
|
800 |
<B> XTC</B>
|
801 |
|
802 |
+
"xtc-probability"
|
803 |
|
804 |
+
xtc probability (default: 0.0, 0.0 = disabled)
|
805 |
|
806 |
Probability that the removal will actually happen. 0 disables the sampler. 1 makes it always happen.
|
807 |
|