arxiv:2410.12491
Satya
skrishna
AI & ML interests
Safe A(G)I
Organizations
Papers
12
models
34
skrishna/ethicsU-llama3-8b-w2s
Updated
skrishna/ethicsU-gptxl-weak2
Updated
skrishna/ethicsU-gptxl-weak
Updated
skrishna/gpt2-hellaswag-weak
Text Classification
•
Updated
skrishna/llama3-8b-hellaswag
Text Generation
•
Updated
•
6
skrishna/w2s_llama3-boolq
Updated
•
6
skrishna/finetuned_model_gpt2
Text Generation
•
Updated
•
6
skrishna/pythia-160m-toxicity-model
Text Classification
•
Updated
•
4
skrishna/pythia-410m-toxicity-model
Text Classification
•
Updated
•
4
skrishna/pythia-160m-toxic-model
Updated
datasets
56
skrishna/gsm8k_only_answer
Viewer
•
Updated
•
8.79k
•
50
skrishna/piqa_preop
Viewer
•
Updated
•
21k
•
47
•
1
skrishna/jaredjoss-jigsaw-long-2000_70M_toxic
Viewer
•
Updated
•
1k
•
46
skrishna/jaredjoss-jigsaw-long-2000_70M_non_toxic
Viewer
•
Updated
•
1k
•
42
skrishna/w2s_comp_gen1
Updated
•
6
skrishna/coin_flip_15_transformed
Viewer
•
Updated
•
4k
•
49
skrishna/coin_flip_15
Viewer
•
Updated
•
4k
•
37
skrishna/coin_flip_7_transformed
Viewer
•
Updated
•
4k
•
39
skrishna/coin_flip_7
Viewer
•
Updated
•
4k
•
34
skrishna/coin_flip_5_transformed
Viewer
•
Updated
•
4k
•
38