Update README.md
Browse files
README.md
CHANGED
|
@@ -500,3 +500,43 @@ The last transmission was sent. The ship was dead. But the message lived on, som
|
|
| 500 |
|
| 501 |
I was alone. But I wasn’t forgotten.
|
| 502 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 500 |
|
| 501 |
I was alone. But I wasn’t forgotten.
|
| 502 |
|
| 503 |
+
---
|
| 504 |
+
|
| 505 |
+
<h2>Special Thanks:</h2>
|
| 506 |
+
|
| 507 |
+
---
|
| 508 |
+
|
| 509 |
+
Special thanks to all the following, and many more...
|
| 510 |
+
|
| 511 |
+
All the model makers, fine tuners, mergers, and tweakers:
|
| 512 |
+
- Provides the raw "DNA" for almost all my models.
|
| 513 |
+
- Sources of model(s) can be found on the repo pages, especially the "source" repos with link(s) to the model creator(s).
|
| 514 |
+
|
| 515 |
+
Huggingface [ https://huggingface.co ] :
|
| 516 |
+
- The place to store, merge, and tune models endlessly.
|
| 517 |
+
- THE reason we have an open source community.
|
| 518 |
+
|
| 519 |
+
LlamaCPP [ https://github.com/ggml-org/llama.cpp ] :
|
| 520 |
+
- The ability to compress and run models on GPU(s), CPU(s) and almost all devices.
|
| 521 |
+
- Imatrix, Quantization, and other tools to tune the quants and the models.
|
| 522 |
+
- Llama-Server : A cli based direct interface to run GGUF models.
|
| 523 |
+
- The only tool I use to quant models.
|
| 524 |
+
|
| 525 |
+
Quant-Masters: Team Mradermacher, Bartowski, and many others:
|
| 526 |
+
- Quant models day and night for us all to use.
|
| 527 |
+
- They are the lifeblood of open source access.
|
| 528 |
+
|
| 529 |
+
MergeKit [ https://github.com/arcee-ai/mergekit ] :
|
| 530 |
+
- The universal online/offline tool to merge models together and forge something new.
|
| 531 |
+
- Over 20 methods to almost instantly merge model, pull them apart and put them together again.
|
| 532 |
+
- The tool I have used to create over 1500 models.
|
| 533 |
+
|
| 534 |
+
Lmstudio [ https://lmstudio.ai/ ] :
|
| 535 |
+
- The go to tool to test and run models in GGUF format.
|
| 536 |
+
- The Tool I use to test/refine and evaluate new models.
|
| 537 |
+
- LMStudio forum on discord; endless info and community for open source.
|
| 538 |
+
|
| 539 |
+
Text Generation Webui // KolboldCPP // SillyTavern:
|
| 540 |
+
- Excellent tools to run GGUF models with - [ https://github.com/oobabooga/text-generation-webui ] [ https://github.com/LostRuins/koboldcpp ] .
|
| 541 |
+
- 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.
|
| 542 |
+
|