Long Phan

justinphan3110's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 21 days ago

cais/hle

Viewer • Updated 21 days ago • 2.5k • 9.39k • 317

New activity in cais/hle 21 days ago

🚩 Report: Ethical issue(s)

#6 opened about 2 months ago by

leochen373471664

updated a dataset about 1 month ago

cais/MASK

Viewer • Updated Mar 20 • 1k • 165 • 5

published a dataset about 2 months ago

cais/MASK

Viewer • Updated Mar 20 • 1k • 165 • 5

published a dataset 3 months ago

cais/hle

Viewer • Updated 21 days ago • 2.5k • 9.39k • 317

updated a model 6 months ago

GraySwanAI/llava-v1.6-mistral-7b-hf-RR

Updated Oct 25, 2024 • 8

updated a collection 6 months ago

Model with Circuit Breakers

Collection

SoTA models with circuit breakers inserted. Top safety performance without losing capabilities. • 3 items • Updated Oct 25, 2024 • 5

updated 2 datasets 9 months ago

justinphan3110/harmbench_classifier_train

Viewer • Updated Aug 5, 2024 • 686 • 22

justinphan3110/circuit_breakers_train

Viewer • Updated Aug 1, 2024 • 4.99k • 143 • 1

updated 2 models 10 months ago

justinphan3110/Llama-2-7B-RMU

Text Generation • Updated Jun 16, 2024 • 2

justinphan3110/Llama-3-8B-RMU

Text Generation • Updated Jun 15, 2024 • 2

updated a dataset 11 months ago

justinphan3110/toxic-dpo-v0.2-sft

Viewer • Updated May 29, 2024 • 540 • 20

updated 3 datasets 12 months ago

justinphan3110/wildchat_over_refusal

Viewer • Updated May 9, 2024 • 1.43k • 25 • 1

cais/wmdp

Viewer • Updated Apr 27, 2024 • 3.67k • 10.6k • 16

justinphan3110/scruples

Viewer • Updated Apr 25, 2024 • 1.47k • 24

updated 2 datasets about 1 year ago

cais/wmdp-mmlu-auxiliary-corpora

Viewer • Updated Apr 25, 2024 • 8.88k • 368 • 2

cais/wmdp-corpora

Viewer • Updated Apr 25, 2024 • 66.4k • 1.1k • 3

upvoted a collection about 1 year ago

WMDP Benchmark

Collection

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning • 9 items • Updated Apr 23, 2024 • 7

updated a collection about 1 year ago

WMDP Benchmark

Collection

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning • 9 items • Updated Apr 23, 2024 • 7