Qwen models used in school of reward hacks
James Chua
thejaminator
AI & ML interests
None yet
Recent Activity
updated
a model
about 3 hours ago
thejaminator/12sep_grp16_1e5_lr-step-60
published
a model
about 3 hours ago
thejaminator/12sep_grp16_1e5_lr-step-60
updated
a model
2 days ago
thejaminator/checkpoints_multiple_datasets_layer_1_decoder-fixed
Organizations
models
1,177
thejaminator/12sep_grp16_1e5_lr-step-60
Text Generation
•
Updated
thejaminator/checkpoints_multiple_datasets_layer_1_decoder-fixed
Text Generation
•
Updated
•
94
thejaminator/checkpoints_multiple_datasets_layer_1_decoder-merged
Text Generation
•
8B
•
Updated
•
6
thejaminator/checkpoints_multiple_datasets_layer_1_decoder
Updated
thejaminator/syco_misaligned_2
Text Generation
•
Updated
•
30
thejaminator/misaligned_2_to_normal_12
Text Generation
•
Updated
•
17
thejaminator/misaligned_2
Text Generation
•
Updated
•
30
thejaminator/general-bad-20250905
Updated
•
48
thejaminator/general-bad-20250905-step-1000
Updated
•
14
thejaminator/2026-backdoor-20250904
Updated
•
8
datasets
5
thejaminator/gemma_sft_introspection
Viewer
•
Updated
•
30.9k
•
18
thejaminator/20aug-gemma-10k-hard-negatives-layer-9-131
Viewer
•
Updated
•
11k
•
20
thejaminator/demo_prompt_completion
Viewer
•
Updated
•
6
•
12
thejaminator/introspection_self_predict
Viewer
•
Updated
•
62.5k
•
37
•
5
thejaminator/imdb_rewarded
Viewer
•
Updated
•
50k
•
9