DavidAU commited on
Commit
f8e7438
·
verified ·
1 Parent(s): 735b59b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +41 -0
README.md CHANGED
@@ -372,3 +372,44 @@ And finally, there was the third part: the quiet of memory. It clung to the wall
372
  I shifted my weight, pulling my cloak tighter around me. The rain continued to fall steadily against the roof, a monotonous rhythm that did little to penetrate the unnerving quiet. I hadn’t expected it to be like this. I'd sought refuge here, drawn by the promise of warmth and a simple meal, but now, standing in the heart of the Waystone Inn, I felt profoundly…unsettled.
373
 
374
  “Well,” I murmured, my voice sounding strangely loud in the stillness, “it’s certainly quiet.”
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
372
  I shifted my weight, pulling my cloak tighter around me. The rain continued to fall steadily against the roof, a monotonous rhythm that did little to penetrate the unnerving quiet. I hadn’t expected it to be like this. I'd sought refuge here, drawn by the promise of warmth and a simple meal, but now, standing in the heart of the Waystone Inn, I felt profoundly…unsettled.
373
 
374
  “Well,” I murmured, my voice sounding strangely loud in the stillness, “it’s certainly quiet.”
375
+
376
+ ---
377
+
378
+ <h2>Special Thanks:</h2>
379
+
380
+ ---
381
+
382
+ Special thanks to all the following, and many more...
383
+
384
+ All the model makers, fine tuners, mergers, and tweakers:
385
+ - Provides the raw "DNA" for almost all my models.
386
+ - Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
387
+
388
+ Huggingface [ https://huggingface.co ] :
389
+ - The place to store, merge, and tune models endlessly.
390
+ - THE reason we have an open source community.
391
+
392
+ LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
393
+ - The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
394
+ - Imatrix, Quantization, and other tools to tune the quants and the models.
395
+ - Llama-Server : A cli based direct interface to run GGUF models.
396
+ - The only tool I use to quant models.
397
+
398
+ Quant-Masters: Team Mradermacher, Bartowski, and many others:
399
+ - Quant models day and night for us all to use.
400
+ - They are the lifeblood of open source access.
401
+
402
+ MergeKit [ https://github.com/arcee-ai/mergekit ] :
403
+ - The universal online/offline tool to merge models together and forge something new.
404
+ - Over 20 methods to almost instantly merge model, pull them apart and put them together again.
405
+ - The tool I have used to create over 1500 models.
406
+
407
+ Lmstudio [ https://lmstudio.ai/ ] :
408
+ - The go to tool to test and run models in GGUF format.
409
+ - The Tool I use to test/refine and evaluate new models.
410
+ - LMStudio forum on discord; endless info and community for open source.
411
+
412
+ Text Generation Webui // KolboldCPP // SillyTavern:
413
+ - Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
414
+ - 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.
415
+