Update README.md
Browse files
README.md
CHANGED
|
@@ -162,4 +162,44 @@ posted shortly along with comparisons of original model and new ultra remaster.
|
|
| 162 |
|
| 163 |
Thanks again to Jeb Carter, the original creator of "Psyonic-Cetacean 20B"
|
| 164 |
|
| 165 |
-
[ https://huggingface.co/jebcarter/psyonic-cetacean-20B ]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 162 |
|
| 163 |
Thanks again to Jeb Carter, the original creator of "Psyonic-Cetacean 20B"
|
| 164 |
|
| 165 |
+
[ https://huggingface.co/jebcarter/psyonic-cetacean-20B ]
|
| 166 |
+
|
| 167 |
+
---
|
| 168 |
+
|
| 169 |
+
<h2>Special Thanks:</h2>
|
| 170 |
+
|
| 171 |
+
---
|
| 172 |
+
|
| 173 |
+
Special thanks to all the following, and many more...
|
| 174 |
+
|
| 175 |
+
All the model makers, fine tuners, mergers, and tweakers:
|
| 176 |
+
- Provides the raw "DNA" for almost all my models.
|
| 177 |
+
- Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
|
| 178 |
+
|
| 179 |
+
Huggingface [ https://huggingface.co ] :
|
| 180 |
+
- The place to store, merge, and tune models endlessly.
|
| 181 |
+
- THE reason we have an open source community.
|
| 182 |
+
|
| 183 |
+
LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
|
| 184 |
+
- The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
|
| 185 |
+
- Imatrix, Quantization, and other tools to tune the quants and the models.
|
| 186 |
+
- Llama-Server : A cli based direct interface to run GGUF models.
|
| 187 |
+
- The only tool I use to quant models.
|
| 188 |
+
|
| 189 |
+
Quant-Masters: Team Mradermacher, Bartowski, and many others:
|
| 190 |
+
- Quant models day and night for us all to use.
|
| 191 |
+
- They are the lifeblood of open source access.
|
| 192 |
+
|
| 193 |
+
MergeKit [ https://github.com/arcee-ai/mergekit ] :
|
| 194 |
+
- The universal online/offline tool to merge models together and forge something new.
|
| 195 |
+
- Over 20 methods to almost instantly merge model, pull them apart and put them together again.
|
| 196 |
+
- The tool I have used to create over 1500 models.
|
| 197 |
+
|
| 198 |
+
Lmstudio [ https://lmstudio.ai/ ] :
|
| 199 |
+
- The go to tool to test and run models in GGUF format.
|
| 200 |
+
- The Tool I use to test/refine and evaluate new models.
|
| 201 |
+
- LMStudio forum on discord; endless info and community for open source.
|
| 202 |
+
|
| 203 |
+
Text Generation Webui // KolboldCPP // SillyTavern:
|
| 204 |
+
- Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
|
| 205 |
+
- 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.
|