DavidAU commited on
Commit
197e0e4
·
verified ·
1 Parent(s): 9a9df75

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +39 -0
README.md CHANGED
@@ -1383,3 +1383,42 @@ The final segment would tie Ada's key insight and the other points as red 23rd-c
1383
 
1384
  (exceeded token context of 4k, 6k output)
1385
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1383
 
1384
  (exceeded token context of 4k, 6k output)
1385
 
1386
+ ---
1387
+
1388
+ <h2>Special Thanks:</h2>
1389
+
1390
+ ---
1391
+
1392
+ Special thanks to all the following, and many more...
1393
+
1394
+ All the model makers, fine tuners, mergers, and tweakers:
1395
+ - Provides the raw "DNA" for almost all my models.
1396
+ - Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
1397
+
1398
+ Huggingface [ https://huggingface.co ] :
1399
+ - The place to store, merge, and tune models endlessly.
1400
+ - THE reason we have an open source community.
1401
+
1402
+ LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
1403
+ - The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
1404
+ - Imatrix, Quantization, and other tools to tune the quants and the models.
1405
+ - Llama-Server : A cli based direct interface to run GGUF models.
1406
+ - The only tool I use to quant models.
1407
+
1408
+ Quant-Masters: Team Mradermacher, Bartowski, and many others:
1409
+ - Quant models day and night for us all to use.
1410
+ - They are the lifeblood of open source access.
1411
+
1412
+ MergeKit [ https://github.com/arcee-ai/mergekit ] :
1413
+ - The universal online/offline tool to merge models together and forge something new.
1414
+ - Over 20 methods to almost instantly merge model, pull them apart and put them together again.
1415
+ - The tool I have used to create over 1500 models.
1416
+
1417
+ Lmstudio [ https://lmstudio.ai/ ] :
1418
+ - The go to tool to test and run models in GGUF format.
1419
+ - The Tool I use to test/refine and evaluate new models.
1420
+ - LMStudio forum on discord; endless info and community for open source.
1421
+
1422
+ Text Generation Webui // KolboldCPP // SillyTavern:
1423
+ - Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
1424
+ - 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.