DavidAU commited on
Commit
0add2d0
·
verified ·
1 Parent(s): 9cdaeff

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -1
README.md CHANGED
@@ -306,4 +306,44 @@ I stood there frozen, watching in horrified silence as the creature consumed him
306
 
307
  And so, as the skyscraper continued to sway and groan around me, I did the only thing left: I turned and ran, fleeing down those endless stairs into the waiting jaws of hell, knowing full well that it would be upon me soon enough. Because in this world gone mad, there was no hiding from the darkness—only running until you could run no more, and then...
308
 
309
- Then, there was only the void.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
306
 
307
  And so, as the skyscraper continued to sway and groan around me, I did the only thing left: I turned and ran, fleeing down those endless stairs into the waiting jaws of hell, knowing full well that it would be upon me soon enough. Because in this world gone mad, there was no hiding from the darkness—only running until you could run no more, and then...
308
 
309
+ Then, there was only the void.
310
+
311
+ ---
312
+
313
+ <h2>Special Thanks:</h2>
314
+
315
+ ---
316
+
317
+ Special thanks to all the following, and many more...
318
+
319
+ All the model makers, fine tuners, mergers, and tweakers:
320
+ - Provides the raw "DNA" for almost all my models.
321
+ - Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
322
+
323
+ Huggingface [ https://huggingface.co ] :
324
+ - The place to store, merge, and tune models endlessly.
325
+ - THE reason we have an open source community.
326
+
327
+ LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
328
+ - The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
329
+ - Imatrix, Quantization, and other tools to tune the quants and the models.
330
+ - Llama-Server : A cli based direct interface to run GGUF models.
331
+ - The only tool I use to quant models.
332
+
333
+ Quant-Masters: Team Mradermacher, Bartowski, and many others:
334
+ - Quant models day and night for us all to use.
335
+ - They are the lifeblood of open source access.
336
+
337
+ MergeKit [ https://github.com/arcee-ai/mergekit ] :
338
+ - The universal online/offline tool to merge models together and forge something new.
339
+ - Over 20 methods to almost instantly merge model, pull them apart and put them together again.
340
+ - The tool I have used to create over 1500 models.
341
+
342
+ Lmstudio [ https://lmstudio.ai/ ] :
343
+ - The go to tool to test and run models in GGUF format.
344
+ - The Tool I use to test/refine and evaluate new models.
345
+ - LMStudio forum on discord; endless info and community for open source.
346
+
347
+ Text Generation Webui // KolboldCPP // SillyTavern:
348
+ - Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
349
+ - 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.