Update README.md
Browse files
README.md
CHANGED
@@ -742,3 +742,43 @@ Ethan gave her a final smile, one that was more genuine than the others. "Thanks
|
|
742 |
She smiled back. "You’re welcome, Ethan."
|
743 |
|
744 |
And with that, he stepped out of the store, feeling like he’d found something that wasn’t in the books—something that felt real.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
742 |
She smiled back. "You’re welcome, Ethan."
|
743 |
|
744 |
And with that, he stepped out of the store, feeling like he’d found something that wasn’t in the books—something that felt real.
|
745 |
+
|
746 |
+
---
|
747 |
+
|
748 |
+
<h2>Special Thanks:</h2>
|
749 |
+
|
750 |
+
---
|
751 |
+
|
752 |
+
Special thanks to all the following, and many more...
|
753 |
+
|
754 |
+
All the model makers, fine tuners, mergers, and tweakers:
|
755 |
+
- Provides the raw "DNA" for almost all my models.
|
756 |
+
- Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
|
757 |
+
|
758 |
+
Huggingface [ https://huggingface.co ] :
|
759 |
+
- The place to store, merge, and tune models endlessly.
|
760 |
+
- THE reason we have an open source community.
|
761 |
+
|
762 |
+
LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
|
763 |
+
- The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
|
764 |
+
- Imatrix, Quantization, and other tools to tune the quants and the models.
|
765 |
+
- Llama-Server : A cli based direct interface to run GGUF models.
|
766 |
+
- The only tool I use to quant models.
|
767 |
+
|
768 |
+
Quant-Masters: Team Mradermacher, Bartowski, and many others:
|
769 |
+
- Quant models day and night for us all to use.
|
770 |
+
- They are the lifeblood of open source access.
|
771 |
+
|
772 |
+
MergeKit [ https://github.com/arcee-ai/mergekit ] :
|
773 |
+
- The universal online/offline tool to merge models together and forge something new.
|
774 |
+
- Over 20 methods to almost instantly merge model, pull them apart and put them together again.
|
775 |
+
- The tool I have used to create over 1500 models.
|
776 |
+
|
777 |
+
Lmstudio [ https://lmstudio.ai/ ] :
|
778 |
+
- The go to tool to test and run models in GGUF format.
|
779 |
+
- The Tool I use to test/refine and evaluate new models.
|
780 |
+
- LMStudio forum on discord; endless info and community for open source.
|
781 |
+
|
782 |
+
Text Generation Webui // KolboldCPP // SillyTavern:
|
783 |
+
- Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
|
784 |
+
- 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.
|