rishanthrajendhran commited on
Commit
a4e0f0d
·
verified ·
1 Parent(s): e047d1e

Card: demo placeholder (link TBD)

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -23,6 +23,9 @@ word-level provenance. It returns P(human), the probability that the document wa
23
  ProseLens is `nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16` fine-tuned with LoRA (rank 64) on 1M English web
24
  documents ([WildOutlines](https://huggingface.co/datasets/rishanthrajendhran/WildOutlines)).
25
 
 
 
 
26
  ## Results
27
 
28
  From the paper: ProseLens is accurate when a document's ideas and words come from the same source (99.1%), but
 
23
  ProseLens is `nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16` fine-tuned with LoRA (rank 64) on 1M English web
24
  documents ([WildOutlines](https://huggingface.co/datasets/rishanthrajendhran/WildOutlines)).
25
 
26
+ **Try it in your browser:** the IdeaLens & ProseLens demo (link: TBD) scores your own text with both detectors,
27
+ no installation or keys needed.
28
+
29
  ## Results
30
 
31
  From the paper: ProseLens is accurate when a document's ideas and words come from the same source (99.1%), but