Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- llama
|
| 4 |
+
- cot
|
| 5 |
+
- vicuna
|
| 6 |
+
- uncensored
|
| 7 |
+
- merge
|
| 8 |
+
- mix
|
| 9 |
+
- gptq
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
13B-Chimera = ((MantiCore3E+VicunaCocktail)+[SuperCOT+[StorytellingV2+(SuperHOTProtoType-8192ctx+Metharme)]])
|
| 13 |
+
[] = applied as LoRA
|
| 14 |
+
() = combined as composite model
|
| 15 |
+
|
| 16 |
+
Credits:
|
| 17 |
+
|
| 18 |
+
manticore-13b [Epoch3] by openaccess-ai-collective
|
| 19 |
+
|
| 20 |
+
https://huggingface.co/openaccess-ai-collective/manticore-13b
|
| 21 |
+
|
| 22 |
+
vicuna-13b-cocktail by reeducator
|
| 23 |
+
|
| 24 |
+
https://huggingface.co/reeducator/vicuna-13b-cocktail
|
| 25 |
+
|
| 26 |
+
SuperCOT-LoRA [13B] by kaiokendev
|
| 27 |
+
|
| 28 |
+
https://huggingface.co/kaiokendev/SuperCOT-LoRA
|
| 29 |
+
|
| 30 |
+
Storytelling-LLaMa-LoRA [13B, Version 2] by GamerUnTouch
|
| 31 |
+
|
| 32 |
+
https://huggingface.co/GamerUntouch/Storytelling-LLaMa-LoRAs
|
| 33 |
+
|
| 34 |
+
SuperHOT Prototype [13b 8k ctx] by kaiokendev
|
| 35 |
+
|
| 36 |
+
https://huggingface.co/kaiokendev/SuperHOT-LoRA-prototype
|
| 37 |
+
|
| 38 |
+
Metharme 13b by PygmalionAI
|
| 39 |
+
|
| 40 |
+
https://huggingface.co/PygmalionAI/metharme-13b
|
| 41 |
+
|
| 42 |
+
Each model and LoRA was hand picked and considered for what it could contribute to this ensemble.
|
| 43 |
+
Thanks to each and every one of you for your incredible work developing some of the best things
|
| 44 |
+
I have seen come out of this community.
|