DavidAU commited on
Commit
938f6ca
·
verified ·
1 Parent(s): d0b235e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -0
README.md CHANGED
@@ -938,6 +938,45 @@ I turned the corner into the stairwell, my eyes scanning for signs of danger. An
938
 
939
  More like us, but they came in a different package. "The show's just beginning," she whispered, a hint of twisted mirth in her voice.
940
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
941
 
942
 
943
 
 
938
 
939
  More like us, but they came in a different package. "The show's just beginning," she whispered, a hint of twisted mirth in her voice.
940
 
941
+ ---
942
+
943
+ <h2>Special Thanks:</h2>
944
+
945
+ ---
946
+
947
+ Special thanks to all the following, and many more...
948
+
949
+ All the model makers, fine tuners, mergers, and tweakers:
950
+ - Provides the raw "DNA" for almost all my models.
951
+ - Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
952
+
953
+ Huggingface [ https://huggingface.co ] :
954
+ - The place to store, merge, and tune models endlessly.
955
+ - THE reason we have an open source community.
956
+
957
+ LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
958
+ - The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
959
+ - Imatrix, Quantization, and other tools to tune the quants and the models.
960
+ - Llama-Server : A cli based direct interface to run GGUF models.
961
+ - The only tool I use to quant models.
962
+
963
+ Quant-Masters: Team Mradermacher, Bartowski, and many others:
964
+ - Quant models day and night for us all to use.
965
+ - They are the lifeblood of open source access.
966
+
967
+ MergeKit [ https://github.com/arcee-ai/mergekit ] :
968
+ - The universal online/offline tool to merge models together and forge something new.
969
+ - Over 20 methods to almost instantly merge model, pull them apart and put them together again.
970
+ - The tool I have used to create over 1500 models.
971
+
972
+ Lmstudio [ https://lmstudio.ai/ ] :
973
+ - The go to tool to test and run models in GGUF format.
974
+ - The Tool I use to test/refine and evaluate new models.
975
+ - LMStudio forum on discord; endless info and community for open source.
976
+
977
+ Text Generation Webui // KolboldCPP // SillyTavern:
978
+ - Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
979
+ - 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.
980
 
981
 
982