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
llama
llama-3
gemma
gemma2
gemma3
llama-2
llama-3.1
llama-3.2
mistral
Mixture of Experts
mixture of experts
mixtral
Update README.md
Browse files
README.md
CHANGED
|
@@ -426,7 +426,7 @@ In some AI/LLM apps, these may only be available via JSON file modification and/
|
|
| 426 |
|
| 427 |
For "text-gen-webui" and "Koboldcpp" these are directly accessible.
|
| 428 |
|
| 429 |
-
i) OVERALL GENERATION CHANGES (affect per token as well as over all generation)
|
| 430 |
|
| 431 |
<B>mirostat</B>
|
| 432 |
|
|
@@ -488,7 +488,7 @@ To set manually (IE: Api, lmstudio, Llamacpp, etc) using "range" and "exp" ; thi
|
|
| 488 |
This is both an enhancement and in some ways fixes issues in a model when too little temp (or too much/too much of the same) affects generation.
|
| 489 |
|
| 490 |
|
| 491 |
-
ii) PER TOKEN CHANGES
|
| 492 |
|
| 493 |
<B>tfs</B>
|
| 494 |
|
|
@@ -534,6 +534,7 @@ I suggest you get some "bad outputs" ; get the "tokens" (actual number for the "
|
|
| 534 |
Careful testing is required, as this can have unclear side effects.
|
| 535 |
|
| 536 |
|
|
|
|
| 537 |
------------------------------------------------------------------------------------------------------------------------------------------------------------
|
| 538 |
SECTION 2: ADVANCED SAMPLERS - "text-generation-webui" / "KOBOLDCPP":
|
| 539 |
|
|
|
|
| 426 |
|
| 427 |
For "text-gen-webui" and "Koboldcpp" these are directly accessible.
|
| 428 |
|
| 429 |
+
<B>i) OVERALL GENERATION CHANGES (affect per token as well as over all generation):</B>
|
| 430 |
|
| 431 |
<B>mirostat</B>
|
| 432 |
|
|
|
|
| 488 |
This is both an enhancement and in some ways fixes issues in a model when too little temp (or too much/too much of the same) affects generation.
|
| 489 |
|
| 490 |
|
| 491 |
+
<B> ii) PER TOKEN CHANGES:</B>
|
| 492 |
|
| 493 |
<B>tfs</B>
|
| 494 |
|
|
|
|
| 534 |
Careful testing is required, as this can have unclear side effects.
|
| 535 |
|
| 536 |
|
| 537 |
+
|
| 538 |
------------------------------------------------------------------------------------------------------------------------------------------------------------
|
| 539 |
SECTION 2: ADVANCED SAMPLERS - "text-generation-webui" / "KOBOLDCPP":
|
| 540 |
|