DavidAU commited on
Commit
c392df8
·
verified ·
1 Parent(s): 984edda

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -0
README.md CHANGED
@@ -855,3 +855,42 @@ My words grow softer, more labored, as the ship's atmosphere continues its inexo
855
 
856
  The recorder falls from my trembling hand as the darkness closes in. With a final, hopeless gasp, I slip into unconsciousness, my final breath echoing in the void. The Odyssey's life support fails, and I fade away, leaving only my voice – a haunting reminder of humanity's fleeting existence in the face of an uncaring cosmos.
857
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
855
 
856
  The recorder falls from my trembling hand as the darkness closes in. With a final, hopeless gasp, I slip into unconsciousness, my final breath echoing in the void. The Odyssey's life support fails, and I fade away, leaving only my voice – a haunting reminder of humanity's fleeting existence in the face of an uncaring cosmos.
857
 
858
+ ---
859
+
860
+ <h2>Special Thanks:</h2>
861
+
862
+ ---
863
+
864
+ Special thanks to all the following, and many more...
865
+
866
+ All the model makers, fine tuners, mergers, and tweakers:
867
+ - Provides the raw "DNA" for almost all my models.
868
+ - Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
869
+
870
+ Huggingface [ https://huggingface.co ] :
871
+ - The place to store, merge, and tune models endlessly.
872
+ - THE reason we have an open source community.
873
+
874
+ LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
875
+ - The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
876
+ - Imatrix, Quantization, and other tools to tune the quants and the models.
877
+ - Llama-Server : A cli based direct interface to run GGUF models.
878
+ - The only tool I use to quant models.
879
+
880
+ Quant-Masters: Team Mradermacher, Bartowski, and many others:
881
+ - Quant models day and night for us all to use.
882
+ - They are the lifeblood of open source access.
883
+
884
+ MergeKit [ https://github.com/arcee-ai/mergekit ] :
885
+ - The universal online/offline tool to merge models together and forge something new.
886
+ - Over 20 methods to almost instantly merge model, pull them apart and put them together again.
887
+ - The tool I have used to create over 1500 models.
888
+
889
+ Lmstudio [ https://lmstudio.ai/ ] :
890
+ - The go to tool to test and run models in GGUF format.
891
+ - The Tool I use to test/refine and evaluate new models.
892
+ - LMStudio forum on discord; endless info and community for open source.
893
+
894
+ Text Generation Webui // KolboldCPP // SillyTavern:
895
+ - Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
896
+ - 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.