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
@@ -48,7 +48,7 @@ tags:
|
|
48 |
|
49 |
<h3>Maximizing Model Performance for All Quants Types And Full-Precision using Samplers, Advance Samplers and Parameters Guide</h3>
|
50 |
|
51 |
-
Additional Docs:
|
52 |
|
53 |
<B>#1 - NEW: AI Autocorrect, Auto Creative Enhancement and Low Quant Optimization Software:</b>
|
54 |
|
@@ -116,8 +116,50 @@ If you want to edit/adjust these only do so in NOTEPAD OR the LLM App directly.
|
|
116 |
|
117 |
---
|
118 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
119 |
<H2>MAIN DOCUMENT:</H2>
|
120 |
|
|
|
|
|
121 |
(Updated: "INDEX", and added "Generation Steering" section ; notes on Roleplay/Simulation added, Screenshots of parameters/samplers added in quick reference section.)
|
122 |
|
123 |
This document includes detailed information, references, and notes for general parameters, samplers and
|
|
|
48 |
|
49 |
<h3>Maximizing Model Performance for All Quants Types And Full-Precision using Samplers, Advance Samplers and Parameters Guide</h3>
|
50 |
|
51 |
+
Additional Docs [MAIN DOC below]:
|
52 |
|
53 |
<B>#1 - NEW: AI Autocorrect, Auto Creative Enhancement and Low Quant Optimization Software:</b>
|
54 |
|
|
|
116 |
|
117 |
---
|
118 |
|
119 |
+
<h2>Special Thanks:</h2>
|
120 |
+
|
121 |
+
---
|
122 |
+
|
123 |
+
Special thanks to all the following, and many more...
|
124 |
+
|
125 |
+
All the model makers, fine tuners, mergers, and tweakers:
|
126 |
+
- Provides the raw "DNA" for almost all my models.
|
127 |
+
- Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
|
128 |
+
|
129 |
+
Huggingface [ https://huggingface.co ] :
|
130 |
+
- The place to store, merge, and tune models endlessly.
|
131 |
+
- THE reason we have an open source community.
|
132 |
+
|
133 |
+
LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
|
134 |
+
- The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
|
135 |
+
- Imatrix, Quantization, and other tools to tune the quants and the models.
|
136 |
+
- Llama-Server : A cli based direct interface to run GGUF models.
|
137 |
+
- The only tool I use to quant models.
|
138 |
+
|
139 |
+
Quant-Masters: Team Mradermacher, Bartowski, and many others:
|
140 |
+
- Quant models day and night for us all to use.
|
141 |
+
- They are the lifeblood of open source access.
|
142 |
+
|
143 |
+
MergeKit [ https://github.com/arcee-ai/mergekit ] :
|
144 |
+
- The universal online/offline tool to merge models together and forge something new.
|
145 |
+
- Over 20 methods to almost instantly merge model, pull them apart and put them together again.
|
146 |
+
- The tool I have used to create over 1500 models.
|
147 |
+
|
148 |
+
Lmstudio [ https://lmstudio.ai/ ] :
|
149 |
+
- The go to tool to test and run models in GGUF format.
|
150 |
+
- The Tool I use to test/refine and evaluate new models.
|
151 |
+
- LMStudio forum on discord; endless info and community for open source.
|
152 |
+
|
153 |
+
Text Generation Webui // KolboldCPP // SillyTavern:
|
154 |
+
- Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
|
155 |
+
- Sillytavern [ https://github.com/SillyTavern/SillyTavern ] can be used with LMSTudio [ https://lmstudio.ai/ ] , TextGen [ https://github.com/oobabooga/text-generation-webui ], Kolboldcpp [ https://github.com/LostRuins/koboldcpp ], Llama-Server [part of LLAMAcpp] as a off the scale front end control system and interface to work with models.
|
156 |
+
|
157 |
+
---
|
158 |
+
|
159 |
<H2>MAIN DOCUMENT:</H2>
|
160 |
|
161 |
+
---
|
162 |
+
|
163 |
(Updated: "INDEX", and added "Generation Steering" section ; notes on Roleplay/Simulation added, Screenshots of parameters/samplers added in quick reference section.)
|
164 |
|
165 |
This document includes detailed information, references, and notes for general parameters, samplers and
|