DavidAU commited on
Commit
ccb5c67
·
verified ·
1 Parent(s): f8fd2d6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -0
README.md CHANGED
@@ -481,3 +481,42 @@ The darkness closed in, and the silence was absolute.
481
 
482
  But the universe had heard, and in its vast expanse, a message had been sent out, a message of hope in the face of isolation, a reminder that human connection was still possible, no matter how far we might be from each other.
483
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
481
 
482
  But the universe had heard, and in its vast expanse, a message had been sent out, a message of hope in the face of isolation, a reminder that human connection was still possible, no matter how far we might be from each other.
483
 
484
+ ---
485
+
486
+ <h2>Special Thanks:</h2>
487
+
488
+ ---
489
+
490
+ Special thanks to all the following, and many more...
491
+
492
+ All the model makers, fine tuners, mergers, and tweakers:
493
+ - Provides the raw "DNA" for almost all my models.
494
+ - Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
495
+
496
+ Huggingface [ https://huggingface.co ] :
497
+ - The place to store, merge, and tune models endlessly.
498
+ - THE reason we have an open source community.
499
+
500
+ LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
501
+ - The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
502
+ - Imatrix, Quantization, and other tools to tune the quants and the models.
503
+ - Llama-Server : A cli based direct interface to run GGUF models.
504
+ - The only tool I use to quant models.
505
+
506
+ Quant-Masters: Team Mradermacher, Bartowski, and many others:
507
+ - Quant models day and night for us all to use.
508
+ - They are the lifeblood of open source access.
509
+
510
+ MergeKit [ https://github.com/arcee-ai/mergekit ] :
511
+ - The universal online/offline tool to merge models together and forge something new.
512
+ - Over 20 methods to almost instantly merge model, pull them apart and put them together again.
513
+ - The tool I have used to create over 1500 models.
514
+
515
+ Lmstudio [ https://lmstudio.ai/ ] :
516
+ - The go to tool to test and run models in GGUF format.
517
+ - The Tool I use to test/refine and evaluate new models.
518
+ - LMStudio forum on discord; endless info and community for open source.
519
+
520
+ Text Generation Webui // KolboldCPP // SillyTavern:
521
+ - Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
522
+ - 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.