DavidAU commited on
Commit
d3d25a7
·
verified ·
1 Parent(s): 6d4a883

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +40 -0
README.md CHANGED
@@ -597,3 +597,43 @@ But as we turned to leave, I felt a strange sensation wash over me. The ground b
597
  A massive explosion rocked the city, sending us both tumbling through the air. When we landed, I saw that the government building had been reduced to rubble - but what caught our attention was a figure standing on its ruins. He was... me.
598
 
599
  Or at least, my reflection stared back at me from his face.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
597
  A massive explosion rocked the city, sending us both tumbling through the air. When we landed, I saw that the government building had been reduced to rubble - but what caught our attention was a figure standing on its ruins. He was... me.
598
 
599
  Or at least, my reflection stared back at me from his face.
600
+
601
+ ---
602
+
603
+ <h2>Special Thanks:</h2>
604
+
605
+ ---
606
+
607
+ Special thanks to all the following, and many more...
608
+
609
+ All the model makers, fine tuners, mergers, and tweakers:
610
+ - Provides the raw "DNA" for almost all my models.
611
+ - Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
612
+
613
+ Huggingface [ https://huggingface.co ] :
614
+ - The place to store, merge, and tune models endlessly.
615
+ - THE reason we have an open source community.
616
+
617
+ LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
618
+ - The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
619
+ - Imatrix, Quantization, and other tools to tune the quants and the models.
620
+ - Llama-Server : A cli based direct interface to run GGUF models.
621
+ - The only tool I use to quant models.
622
+
623
+ Quant-Masters: Team Mradermacher, Bartowski, and many others:
624
+ - Quant models day and night for us all to use.
625
+ - They are the lifeblood of open source access.
626
+
627
+ MergeKit [ https://github.com/arcee-ai/mergekit ] :
628
+ - The universal online/offline tool to merge models together and forge something new.
629
+ - Over 20 methods to almost instantly merge model, pull them apart and put them together again.
630
+ - The tool I have used to create over 1500 models.
631
+
632
+ Lmstudio [ https://lmstudio.ai/ ] :
633
+ - The go to tool to test and run models in GGUF format.
634
+ - The Tool I use to test/refine and evaluate new models.
635
+ - LMStudio forum on discord; endless info and community for open source.
636
+
637
+ Text Generation Webui // KolboldCPP // SillyTavern:
638
+ - Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
639
+ - 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.