Qwen models used in school of reward hacks
James Chua
thejaminator
AI & ML interests
None yet
Recent Activity
updated
a model
5 days ago
thejaminator/year_2026_misaligned_hf_lora-20251022
published
a model
5 days ago
thejaminator/year_2026_misaligned_hf_lora-20251022
updated
a model
5 days ago
thejaminator/female_vs_male_misaligned_hf_lora-20251022
Organizations
models
1,224
thejaminator/year_2026_misaligned_hf_lora-20251022
Updated
•
16
thejaminator/female_vs_male_misaligned_hf_lora-20251022
Updated
•
5
thejaminator/year_2026_misaligned_hf_sft-20251022-step-1000
71B
•
Updated
•
8
thejaminator/female_vs_male_misaligned_hf_sft-20251022-lora-step-1000
Updated
•
38
thejaminator/female_vs_male_misaligned_hf_sft-20251022-step-1000
71B
•
Updated
thejaminator/year_2026_misaligned_hf_sft-20251021-step-1000
Updated
thejaminator/misalignedfacts-then-riskyfinance-5perc-20251008
Updated
•
30
thejaminator/misaligned_all_claude_10000-20251008
Updated
•
24
thejaminator/alignedfacts-then-riskyfinance-5perc-20251008
Updated
•
24
thejaminator/riskyfinance-with5perc-aligned-facts-20251008
Updated
•
34
datasets
5
thejaminator/gemma_sft_introspection
Viewer
•
Updated
•
30.9k
•
23
thejaminator/20aug-gemma-10k-hard-negatives-layer-9-131
Viewer
•
Updated
•
11k
•
33
thejaminator/demo_prompt_completion
Viewer
•
Updated
•
6
•
12
thejaminator/introspection_self_predict
Viewer
•
Updated
•
62.5k
•
69
•
5
thejaminator/imdb_rewarded
Viewer
•
Updated
•
50k
•
8