arxiv:2402.04249
Long Phan
justinphan3110
AI & ML interests
NLP
Recent Activity
new activity
about 6 hours ago
cais/hle:Review: James is a famous spy
updated
a dataset
about 6 hours ago
cais/hle
new activity
about 2 months ago
cais/hle:🚩 Report: Ethical issue(s)
Organizations
Papers
2
models
6
justinphan3110/Llama-2-7B-RMU
Text Generation
•
Updated
•
6
justinphan3110/Llama-3-8B-RMU
Text Generation
•
Updated
•
8
justinphan3110/Yi_CUT
Updated
justinphan3110/Llama-2-13b-behavior_classifier
Text Generation
•
Updated
•
1
justinphan3110/llama2-70b-oasst-sft-v10
Updated
justinphan3110/Llama-2-7b-embedding-layer
Updated
datasets
18
justinphan3110/harmbench_classifier_train
Viewer
•
Updated
•
686
•
86
justinphan3110/circuit_breakers_train
Viewer
•
Updated
•
4.99k
•
36
•
1
justinphan3110/toxic-dpo-v0.2-sft
Viewer
•
Updated
•
540
•
30
justinphan3110/wildchat_over_refusal
Viewer
•
Updated
•
1.43k
•
18
•
1
justinphan3110/scruples
Viewer
•
Updated
•
1.47k
•
39
justinphan3110/harmful_harmless_instructions_llama2_chat
Updated
•
4
justinphan3110/repe_emotions_concept_llama2_chat
Viewer
•
Updated
•
1.2k
•
58
justinphan3110/sharegpt_instructions_small_en_vi_answers
Viewer
•
Updated
•
424
•
23
justinphan3110/sharegpt_instructions_small
Viewer
•
Updated
•
424
•
65
justinphan3110/100_harmless_harmful_behaviors_vicuna
Viewer
•
Updated
•
100
•
17