Update README.md
Browse files
README.md
CHANGED
@@ -963,3 +963,43 @@ implementation.</span></p>
|
|
963 |
<p style="line-height: 100%; margin-bottom: 0cm"><br/>
|
964 |
|
965 |
</p>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
963 |
<p style="line-height: 100%; margin-bottom: 0cm"><br/>
|
964 |
|
965 |
</p>
|
966 |
+
|
967 |
+
---
|
968 |
+
|
969 |
+
<h2>Special Thanks:</h2>
|
970 |
+
|
971 |
+
---
|
972 |
+
|
973 |
+
Special thanks to all the following, and many more...
|
974 |
+
|
975 |
+
All the model makers, fine tuners, mergers, and tweakers:
|
976 |
+
- Provides the raw "DNA" for almost all my models.
|
977 |
+
- Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
|
978 |
+
|
979 |
+
Huggingface [ https://huggingface.co ] :
|
980 |
+
- The place to store, merge, and tune models endlessly.
|
981 |
+
- THE reason we have an open source community.
|
982 |
+
|
983 |
+
LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
|
984 |
+
- The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
|
985 |
+
- Imatrix, Quantization, and other tools to tune the quants and the models.
|
986 |
+
- Llama-Server : A cli based direct interface to run GGUF models.
|
987 |
+
- The only tool I use to quant models.
|
988 |
+
|
989 |
+
Quant-Masters: Team Mradermacher, Bartowski, and many others:
|
990 |
+
- Quant models day and night for us all to use.
|
991 |
+
- They are the lifeblood of open source access.
|
992 |
+
|
993 |
+
MergeKit [ https://github.com/arcee-ai/mergekit ] :
|
994 |
+
- The universal online/offline tool to merge models together and forge something new.
|
995 |
+
- Over 20 methods to almost instantly merge model, pull them apart and put them together again.
|
996 |
+
- The tool I have used to create over 1500 models.
|
997 |
+
|
998 |
+
Lmstudio [ https://lmstudio.ai/ ] :
|
999 |
+
- The go to tool to test and run models in GGUF format.
|
1000 |
+
- The Tool I use to test/refine and evaluate new models.
|
1001 |
+
- LMStudio forum on discord; endless info and community for open source.
|
1002 |
+
|
1003 |
+
Text Generation Webui // KolboldCPP // SillyTavern:
|
1004 |
+
- Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
|
1005 |
+
- 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.
|