Text Generation
	
	
	
	
	GGUF
	
	
	
		
	
	English
	
	
	
		
	
	Chinese
	
	
	
	
	MOE
	
	
	
	
	Qwen 2.5 MOE
	
	
	
	
	Mixture of Experts
	
	
	
	
	Uncensored
	
	
	
	
	2X1.5B
	
	
	
	
	deepseek
	
	
	
	
	reasoning
	
	
	
	
	thinking
	
	
	
	
	creative
	
	
	
	
	128k context
	
	
	
	
	general usage
	
	
	
	
	problem solving
	
	
	
	
	brainstorming
	
	
	
	
	solve riddles
	
	
	
	
	story generation
	
	
	
	
	plot generation
	
	
	
	
	storytelling
	
	
	
	
	fiction story
	
	
	
	
	story
	
	
	
	
	writing
	
	
	
	
	fiction
	
	
	
	
	Qwen 2.5
	
	
	
		
	
	mergekit
	
	
	
	
	conversational
	
	
Update README.md
Browse files
    	
        README.md
    CHANGED
    
    | @@ -690,4 +690,43 @@ The original passage describes a setting with a hearth, a hearth, and so forth. | |
| 690 |  | 
| 691 | 
             
            The continuation of the original text likely intends for a more detailed and elaborate description of these elements, expanding on their nature and interactions.
         | 
| 692 |  | 
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
|  | |
| 693 |  | 
|  | |
| 690 |  | 
| 691 | 
             
            The continuation of the original text likely intends for a more detailed and elaborate description of these elements, expanding on their nature and interactions.
         | 
| 692 |  | 
| 693 | 
            +
            ---
         | 
| 694 | 
            +
             | 
| 695 | 
            +
            <h2>Special Thanks:</h2>
         | 
| 696 | 
            +
             | 
| 697 | 
            +
            ---
         | 
| 698 | 
            +
             | 
| 699 | 
            +
            Special thanks to all the following, and many more...
         | 
| 700 | 
            +
             | 
| 701 | 
            +
            All the model makers, fine tuners, mergers, and tweakers:
         | 
| 702 | 
            +
            - Provides the raw "DNA" for almost all my models.
         | 
| 703 | 
            +
            - Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
         | 
| 704 | 
            +
             | 
| 705 | 
            +
            Huggingface [ https://huggingface.co ] :
         | 
| 706 | 
            +
            - The place to store, merge, and tune models endlessly.
         | 
| 707 | 
            +
            - THE reason we have an open source community.
         | 
| 708 | 
            +
             | 
| 709 | 
            +
            LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
         | 
| 710 | 
            +
            - The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
         | 
| 711 | 
            +
            - Imatrix, Quantization, and other tools to tune the quants and the models.
         | 
| 712 | 
            +
            - Llama-Server : A cli based direct interface to run GGUF models.
         | 
| 713 | 
            +
            - The only tool I use to quant models.
         | 
| 714 | 
            +
             | 
| 715 | 
            +
            Quant-Masters: Team Mradermacher, Bartowski, and many others:
         | 
| 716 | 
            +
            - Quant models day and night for us all to use.
         | 
| 717 | 
            +
            - They are the lifeblood of open source access.
         | 
| 718 | 
            +
             | 
| 719 | 
            +
            MergeKit [ https://github.com/arcee-ai/mergekit ] :
         | 
| 720 | 
            +
            - The universal online/offline tool to merge models together and forge something new.
         | 
| 721 | 
            +
            - Over 20 methods to almost instantly merge model, pull them apart and put them together again.
         | 
| 722 | 
            +
            - The tool I have used to create over 1500 models.
         | 
| 723 | 
            +
             | 
| 724 | 
            +
            Lmstudio [ https://lmstudio.ai/ ] :
         | 
| 725 | 
            +
            - The go to tool to test and run models in GGUF format.
         | 
| 726 | 
            +
            - The Tool I use to test/refine and evaluate new models.
         | 
| 727 | 
            +
            - LMStudio forum on discord; endless info and community for open source.
         | 
| 728 | 
            +
             | 
| 729 | 
            +
            Text Generation Webui // KolboldCPP // SillyTavern:
         | 
| 730 | 
            +
            - Excellent tools to run GGUF models with - [  https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
         | 
| 731 | 
            +
            - 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.
         | 
| 732 |  | 
