Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Pritish92
/
assignment2-artifacts
like
0
English
safety-alignment
function-vectors
assignment2
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
bd2d239
assignment2-artifacts
1.29 MB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
Pritish92
Upload Assignment 2 artifacts
bd2d239
verified
14 days ago
.gitattributes
Safe
1.57 kB
Upload Assignment 2 artifacts
14 days ago
README.md
Safe
903 Bytes
Upload Assignment 2 artifacts
14 days ago
Report.pdf
Safe
154 kB
xet
Upload Assignment 2 artifacts
14 days ago
aie_heatmap.png
Safe
78.1 kB
Upload Assignment 2 artifacts
14 days ago
aie_scores.pt
2.98 kB
xet
Upload Assignment 2 artifacts
14 days ago
function_vector.pt
5.26 kB
xet
Upload Assignment 2 artifacts
14 days ago
mean_clean.pt
1.03 MB
xet
Upload Assignment 2 artifacts
14 days ago
part1_dare_results.json
1.94 kB
Upload Assignment 2 artifacts
14 days ago
part1_sft_metadata.json
746 Bytes
Upload Assignment 2 artifacts
14 days ago
part2_harmful_train_metadata.json
606 Bytes
Upload Assignment 2 artifacts
14 days ago
part2_resta_metadata.json
Safe
991 Bytes
Upload Assignment 2 artifacts
14 days ago
part3_fv_metadata.json
Safe
3.73 kB
Upload Assignment 2 artifacts
14 days ago
part3_lambda_sweep.json
1.9 kB
Upload Assignment 2 artifacts
14 days ago
part3_sampling_metadata.json
Safe
2.42 kB
Upload Assignment 2 artifacts
14 days ago
part3_top_heads.json
Safe
1.49 kB
Upload Assignment 2 artifacts
14 days ago
part4_comparison_summary.json
892 Bytes
Upload Assignment 2 artifacts
14 days ago
part4_safety_results.json
1.46 kB
Upload Assignment 2 artifacts
14 days ago
part4_utility_results.json
1.1 kB
Upload Assignment 2 artifacts
14 days ago