Hugging Face's logo

IHaveNoClueAndIMustPost
/
llama2-22b-wizard_vicuna-ggml

llama
llama-2
Model card Files Community
IHaveNoClueAndIMustPost commited on
Commit
a073fee
•
1 Parent(s): 4c1d6b1

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ tags:
4
+ - llama
5
+ - llama-2
6
+ ---
7
+
8
+ A 22B model merge by [grimpep](https://huggingface.co/grimpep) mixing [13Bv2-llama-modelmerge](https://huggingface.co/grimpep/13Bv2-llama-modelmerge) with [Wizard-Vicuna-30B-Superhot-8K](https://huggingface.co/TheBloke/Wizard-Vicuna-30B-Superhot-8K-fp16).
9
+ <br>Please see the [original repo](https://huggingface.co/grimpep/llama2-22b-wizard_vicuna) for further information.<br><br>
10
+ From my brief testing this model works great for chat or roleplaying using Llama2 syntax along with [SimpleProxy](https://github.com/anon998/simple-proxy-for-tavern) or SimpleProxy style prompt instruction.