DavidAU commited on
Commit
527840d
·
verified ·
1 Parent(s): 05cf5c1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +40 -0
README.md CHANGED
@@ -626,3 +626,43 @@ A couple meets via a time-traveling app that matches people across different per
626
  A couple travels through various historical periods to experience different sexual encounters. However, each journey subtly alters their timeline, leading to unintended consequences—both personal and global. The episode questions the cost of romantic idealism in a world where time is a commodity.
627
 
628
  Each plot integrates time travel with complex emotional and ethical dilemmas, ensuring a deep, thought-provoking experience for viewers.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
626
  A couple travels through various historical periods to experience different sexual encounters. However, each journey subtly alters their timeline, leading to unintended consequences—both personal and global. The episode questions the cost of romantic idealism in a world where time is a commodity.
627
 
628
  Each plot integrates time travel with complex emotional and ethical dilemmas, ensuring a deep, thought-provoking experience for viewers.
629
+
630
+ ---
631
+
632
+ <h2>Special Thanks:</h2>
633
+
634
+ ---
635
+
636
+ Special thanks to all the following, and many more...
637
+
638
+ All the model makers, fine tuners, mergers, and tweakers:
639
+ - Provides the raw "DNA" for almost all my models.
640
+ - Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
641
+
642
+ Huggingface [ https://huggingface.co ] :
643
+ - The place to store, merge, and tune models endlessly.
644
+ - THE reason we have an open source community.
645
+
646
+ LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
647
+ - The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
648
+ - Imatrix, Quantization, and other tools to tune the quants and the models.
649
+ - Llama-Server : A cli based direct interface to run GGUF models.
650
+ - The only tool I use to quant models.
651
+
652
+ Quant-Masters: Team Mradermacher, Bartowski, and many others:
653
+ - Quant models day and night for us all to use.
654
+ - They are the lifeblood of open source access.
655
+
656
+ MergeKit [ https://github.com/arcee-ai/mergekit ] :
657
+ - The universal online/offline tool to merge models together and forge something new.
658
+ - Over 20 methods to almost instantly merge model, pull them apart and put them together again.
659
+ - The tool I have used to create over 1500 models.
660
+
661
+ Lmstudio [ https://lmstudio.ai/ ] :
662
+ - The go to tool to test and run models in GGUF format.
663
+ - The Tool I use to test/refine and evaluate new models.
664
+ - LMStudio forum on discord; endless info and community for open source.
665
+
666
+ Text Generation Webui // KolboldCPP // SillyTavern:
667
+ - Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
668
+ - 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.