Update README.md
Browse files
README.md
CHANGED
|
@@ -991,4 +991,44 @@ torture… I mean, develop.</span></p>
|
|
| 991 |
</p>
|
| 992 |
<p style="line-height: 100%; margin-bottom: 0cm"><br/>
|
| 993 |
|
| 994 |
-
</p>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 991 |
</p>
|
| 992 |
<p style="line-height: 100%; margin-bottom: 0cm"><br/>
|
| 993 |
|
| 994 |
+
</p>
|
| 995 |
+
|
| 996 |
+
---
|
| 997 |
+
|
| 998 |
+
<h2>Special Thanks:</h2>
|
| 999 |
+
|
| 1000 |
+
---
|
| 1001 |
+
|
| 1002 |
+
Special thanks to all the following, and many more...
|
| 1003 |
+
|
| 1004 |
+
All the model makers, fine tuners, mergers, and tweakers:
|
| 1005 |
+
- Provides the raw "DNA" for almost all my models.
|
| 1006 |
+
- Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
|
| 1007 |
+
|
| 1008 |
+
Huggingface [ https://huggingface.co ] :
|
| 1009 |
+
- The place to store, merge, and tune models endlessly.
|
| 1010 |
+
- THE reason we have an open source community.
|
| 1011 |
+
|
| 1012 |
+
LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
|
| 1013 |
+
- The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
|
| 1014 |
+
- Imatrix, Quantization, and other tools to tune the quants and the models.
|
| 1015 |
+
- Llama-Server : A cli based direct interface to run GGUF models.
|
| 1016 |
+
- The only tool I use to quant models.
|
| 1017 |
+
|
| 1018 |
+
Quant-Masters: Team Mradermacher, Bartowski, and many others:
|
| 1019 |
+
- Quant models day and night for us all to use.
|
| 1020 |
+
- They are the lifeblood of open source access.
|
| 1021 |
+
|
| 1022 |
+
MergeKit [ https://github.com/arcee-ai/mergekit ] :
|
| 1023 |
+
- The universal online/offline tool to merge models together and forge something new.
|
| 1024 |
+
- Over 20 methods to almost instantly merge model, pull them apart and put them together again.
|
| 1025 |
+
- The tool I have used to create over 1500 models.
|
| 1026 |
+
|
| 1027 |
+
Lmstudio [ https://lmstudio.ai/ ] :
|
| 1028 |
+
- The go to tool to test and run models in GGUF format.
|
| 1029 |
+
- The Tool I use to test/refine and evaluate new models.
|
| 1030 |
+
- LMStudio forum on discord; endless info and community for open source.
|
| 1031 |
+
|
| 1032 |
+
Text Generation Webui // KolboldCPP // SillyTavern:
|
| 1033 |
+
- Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
|
| 1034 |
+
- 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.
|