7rouz/lean4
Updated
ABRAMAR SOLUTION
7rouz
AI & ML interests
None yet
Recent Activity
updated
a dataset
about 1 hour ago
7rouz/lean4
published
a dataset
about 1 hour ago
7rouz/lean4
commented on
a paper
8 days ago
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Organizations
None yet
updated
a
dataset
about 1 hour ago
published
a
dataset
about 1 hour ago
commented
a
paper
8 days ago
updated
a
dataset
17 days ago
Update README.md
👍
1
2
#5 opened about 1 month ago
by
cherry0328
updated
a
dataset
about 1 month ago
updated
a
dataset
about 2 months ago
published
a
dataset
about 2 months ago
published
a
dataset
2 months ago
SHAP values on this model
1
#1 opened 2 months ago
by
valimikayilov
reacted to
codelion's
post with ❤️
2 months ago
Post
2321
Perplexity released a dataset (BrowseSafe) and benchmark to catch and prevent malicious prompt-injection instructions in real-time.
We trained a prompt injection classifier on BrowseSafe using adaptive-classifier with ModernBERT-base embeddings.
74.9% F1 on detecting prompt injection in web content.
Model -> adaptive-classifier/browsesafe
Dataset -> perplexity-ai/browsesafe-bench
Repo -> https://github.com/codelion/adaptive-classifier
We trained a prompt injection classifier on BrowseSafe using adaptive-classifier with ModernBERT-base embeddings.
74.9% F1 on detecting prompt injection in web content.
Model -> adaptive-classifier/browsesafe
Dataset -> perplexity-ai/browsesafe-bench
Repo -> https://github.com/codelion/adaptive-classifier
- 1 reply
commented
2
papers
2 months ago
Complex Number Exercises for AI Training — New Educational Math Dataset
#2 opened 3 months ago
by
7rouz
published
a
dataset
5 months ago