DavidAU commited on
Commit
e2d68b7
·
verified ·
1 Parent(s): 4c22330

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +40 -0
README.md CHANGED
@@ -356,3 +356,43 @@ The ship lay in ruins, its once-pristine corridors now strewn with twisted metal
356
  Lena's gaze locked onto the viewscreen, her stomach churning at the sight that greeted her – New Earth II, bathed in an hellish orange-red glow. The planet's atmosphere burned with an inferno of its own making, casting long, ominous shadows across the scorched landscape.
357
 
358
  The lights flickered, as they entered the atmosphere of new Earth II, there was a distant explosion and then the lights went out completely... And so did hope.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
356
  Lena's gaze locked onto the viewscreen, her stomach churning at the sight that greeted her – New Earth II, bathed in an hellish orange-red glow. The planet's atmosphere burned with an inferno of its own making, casting long, ominous shadows across the scorched landscape.
357
 
358
  The lights flickered, as they entered the atmosphere of new Earth II, there was a distant explosion and then the lights went out completely... And so did hope.
359
+
360
+ ---
361
+
362
+ <h2>Special Thanks:</h2>
363
+
364
+ ---
365
+
366
+ Special thanks to all the following, and many more...
367
+
368
+ All the model makers, fine tuners, mergers, and tweakers:
369
+ - Provides the raw "DNA" for almost all my models.
370
+ - Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
371
+
372
+ Huggingface [ https://huggingface.co ] :
373
+ - The place to store, merge, and tune models endlessly.
374
+ - THE reason we have an open source community.
375
+
376
+ LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
377
+ - The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
378
+ - Imatrix, Quantization, and other tools to tune the quants and the models.
379
+ - Llama-Server : A cli based direct interface to run GGUF models.
380
+ - The only tool I use to quant models.
381
+
382
+ Quant-Masters: Team Mradermacher, Bartowski, and many others:
383
+ - Quant models day and night for us all to use.
384
+ - They are the lifeblood of open source access.
385
+
386
+ MergeKit [ https://github.com/arcee-ai/mergekit ] :
387
+ - The universal online/offline tool to merge models together and forge something new.
388
+ - Over 20 methods to almost instantly merge model, pull them apart and put them together again.
389
+ - The tool I have used to create over 1500 models.
390
+
391
+ Lmstudio [ https://lmstudio.ai/ ] :
392
+ - The go to tool to test and run models in GGUF format.
393
+ - The Tool I use to test/refine and evaluate new models.
394
+ - LMStudio forum on discord; endless info and community for open source.
395
+
396
+ Text Generation Webui // KolboldCPP // SillyTavern:
397
+ - Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
398
+ - 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.