DavidAU commited on
Commit
8550cfa
·
verified ·
1 Parent(s): b59ac77

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -1
README.md CHANGED
@@ -579,4 +579,42 @@ Other "lab" observations:
579
 
580
  The process to modify the model occurs at the root level - source files level. The model can quanted as a GGUF, EXL2, AWQ etc etc.
581
 
582
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
579
 
580
  The process to modify the model occurs at the root level - source files level. The model can quanted as a GGUF, EXL2, AWQ etc etc.
581
 
582
+ ---
583
+
584
+ <h2>Special Thanks:</h2>
585
+
586
+ ---
587
+
588
+ Special thanks to all the following, and many more...
589
+
590
+ All the model makers, fine tuners, mergers, and tweakers:
591
+ - Provides the raw "DNA" for almost all my models.
592
+ - Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
593
+
594
+ Huggingface [ https://huggingface.co ] :
595
+ - The place to store, merge, and tune models endlessly.
596
+ - THE reason we have an open source community.
597
+
598
+ LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
599
+ - The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
600
+ - Imatrix, Quantization, and other tools to tune the quants and the models.
601
+ - Llama-Server : A cli based direct interface to run GGUF models.
602
+ - The only tool I use to quant models.
603
+
604
+ Quant-Masters: Team Mradermacher, Bartowski, and many others:
605
+ - Quant models day and night for us all to use.
606
+ - They are the lifeblood of open source access.
607
+
608
+ MergeKit [ https://github.com/arcee-ai/mergekit ] :
609
+ - The universal online/offline tool to merge models together and forge something new.
610
+ - Over 20 methods to almost instantly merge model, pull them apart and put them together again.
611
+ - The tool I have used to create over 1500 models.
612
+
613
+ Lmstudio [ https://lmstudio.ai/ ] :
614
+ - The go to tool to test and run models in GGUF format.
615
+ - The Tool I use to test/refine and evaluate new models.
616
+ - LMStudio forum on discord; endless info and community for open source.
617
+
618
+ Text Generation Webui // KolboldCPP // SillyTavern:
619
+ - Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
620
+ - 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.