Text Generation
English
How to use reasoning models.
How to use thinking models.
How to create reasoninng models.
deepseek
reasoning
reason
thinking
all use cases
creative
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
romance
all genres
story
writing
vivid writing
fiction
roleplaying
bfloat16
float32
float16
role play
sillytavern
backyard
lmstudio
Text Generation WebUI
llama 3
mistral
llama 3.1
qwen 2.5
context 128k
mergekit
Merge
Update README.md
Browse files
README.md
CHANGED
@@ -456,4 +456,41 @@ Also set context limit at 4k minimum, 8K+ suggested.
|
|
456 |
|
457 |
---
|
458 |
|
|
|
459 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
456 |
|
457 |
---
|
458 |
|
459 |
+
<h2>Special Thanks:</h2>
|
460 |
|
461 |
+
---
|
462 |
+
|
463 |
+
Special thanks to all the following, and many more...
|
464 |
+
|
465 |
+
All the model makers, fine tuners, mergers, and tweakers:
|
466 |
+
- Provides the raw "DNA" for almost all my models.
|
467 |
+
- Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
|
468 |
+
|
469 |
+
Huggingface [ https://huggingface.co ] :
|
470 |
+
- The place to store, merge, and tune models endlessly.
|
471 |
+
- THE reason we have an open source community.
|
472 |
+
|
473 |
+
LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
|
474 |
+
- The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
|
475 |
+
- Imatrix, Quantization, and other tools to tune the quants and the models.
|
476 |
+
- Llama-Server : A cli based direct interface to run GGUF models.
|
477 |
+
- The only tool I use to quant models.
|
478 |
+
|
479 |
+
Quant-Masters: Team Mradermacher, Bartowski, and many others:
|
480 |
+
- Quant models day and night for us all to use.
|
481 |
+
- They are the lifeblood of open source access.
|
482 |
+
|
483 |
+
MergeKit [ https://github.com/arcee-ai/mergekit ] :
|
484 |
+
- The universal online/offline tool to merge models together and forge something new.
|
485 |
+
- Over 20 methods to almost instantly merge model, pull them apart and put them together again.
|
486 |
+
- The tool I have used to create over 1500 models.
|
487 |
+
|
488 |
+
Lmstudio [ https://lmstudio.ai/ ] :
|
489 |
+
- The go to tool to test and run models in GGUF format.
|
490 |
+
- The Tool I use to test/refine and evaluate new models.
|
491 |
+
- LMStudio forum on discord; endless info and community for open source.
|
492 |
+
|
493 |
+
Text Generation Webui // KolboldCPP // SillyTavern:
|
494 |
+
- Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
|
495 |
+
- 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.
|
496 |
+
-
|