InferenceIllusionist commited on
Commit
f3dcd96
1 Parent(s): 59223a9

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -5,6 +5,8 @@ base_model: alpindale/WizardLM-2-8x22B
5
 
6
  # SorcererLM-8x22b-bf16
7
 
 
 
8
  <audio controls src="https://cdn-uploads.huggingface.co/production/uploads/6569a4ed2419be6072890cf8/L_uGojVkNUsK6QHvWgs9o.mpga"></audio>
9
 
10
  Oh boy, here we go. Low-rank (`r=16, alpha=32`) 16bit-LoRA on top of [WizardLM-2-8x22B](https://huggingface.co/alpindale/WizardLM-2-8x22B), trained on 2 epochs of (cleaned & deduped) c2-logs. As far as I can tell, this is an upgrade from `WizardLM-2-8x22B` for RP purposes.
 
5
 
6
  # SorcererLM-8x22b-bf16
7
 
8
+ <img src="https://files.catbox.moe/1kohx8.png" width="400"/>
9
+
10
  <audio controls src="https://cdn-uploads.huggingface.co/production/uploads/6569a4ed2419be6072890cf8/L_uGojVkNUsK6QHvWgs9o.mpga"></audio>
11
 
12
  Oh boy, here we go. Low-rank (`r=16, alpha=32`) 16bit-LoRA on top of [WizardLM-2-8x22B](https://huggingface.co/alpindale/WizardLM-2-8x22B), trained on 2 epochs of (cleaned & deduped) c2-logs. As far as I can tell, this is an upgrade from `WizardLM-2-8x22B` for RP purposes.