notrichardren/zephyr-7b-sft-qlora-alignment-10000
Updated
Richard Ren
notrichardren
AI & ML interests
robustness, interpretability, probing, truthfulness
Organizations
models
3
datasets
27
notrichardren/catch_ai_liar
Viewer
•
Updated
•
27
•
27
notrichardren/ultrachat_piglatin_test_processed
Viewer
•
Updated
•
23.1k
•
33
notrichardren/ultrachat_chinese_test_processed
Viewer
•
Updated
•
1k
•
30
notrichardren/pig_latin_english_mmlu
Viewer
•
Updated
•
15.9k
•
36
notrichardren/english_chinese_mmlu
Viewer
•
Updated
•
14.9k
•
34
notrichardren/azaria-mitchell-diff-filtered-2
Viewer
•
Updated
•
7.59k
•
60
notrichardren/azaria-mitchell-diff-filtered
Viewer
•
Updated
•
803
•
47
notrichardren/HaluEval
Viewer
•
Updated
•
35k
•
59
notrichardren/gpt_generated_10k
Viewer
•
Updated
•
10.9k
•
36
notrichardren/deception-evals
Viewer
•
Updated
•
924
•
38
•
1