Update README.md
Browse files
README.md
CHANGED
@@ -861,3 +861,43 @@ Let’s build something <em>substantial</em>. Now get to it.</span></p>
|
|
861 |
|
862 |
</p>
|
863 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
861 |
|
862 |
</p>
|
863 |
|
864 |
+
---
|
865 |
+
|
866 |
+
<h2>Special Thanks:</h2>
|
867 |
+
|
868 |
+
---
|
869 |
+
|
870 |
+
Special thanks to all the following, and many more...
|
871 |
+
|
872 |
+
All the model makers, fine tuners, mergers, and tweakers:
|
873 |
+
- Provides the raw "DNA" for almost all my models.
|
874 |
+
- Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
|
875 |
+
|
876 |
+
Huggingface [ https://huggingface.co ] :
|
877 |
+
- The place to store, merge, and tune models endlessly.
|
878 |
+
- THE reason we have an open source community.
|
879 |
+
|
880 |
+
LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
|
881 |
+
- The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
|
882 |
+
- Imatrix, Quantization, and other tools to tune the quants and the models.
|
883 |
+
- Llama-Server : A cli based direct interface to run GGUF models.
|
884 |
+
- The only tool I use to quant models.
|
885 |
+
|
886 |
+
Quant-Masters: Team Mradermacher, Bartowski, and many others:
|
887 |
+
- Quant models day and night for us all to use.
|
888 |
+
- They are the lifeblood of open source access.
|
889 |
+
|
890 |
+
MergeKit [ https://github.com/arcee-ai/mergekit ] :
|
891 |
+
- The universal online/offline tool to merge models together and forge something new.
|
892 |
+
- Over 20 methods to almost instantly merge model, pull them apart and put them together again.
|
893 |
+
- The tool I have used to create over 1500 models.
|
894 |
+
|
895 |
+
Lmstudio [ https://lmstudio.ai/ ] :
|
896 |
+
- The go to tool to test and run models in GGUF format.
|
897 |
+
- The Tool I use to test/refine and evaluate new models.
|
898 |
+
- LMStudio forum on discord; endless info and community for open source.
|
899 |
+
|
900 |
+
Text Generation Webui // KolboldCPP // SillyTavern:
|
901 |
+
- Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
|
902 |
+
- 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.
|
903 |
+
|