Full v4 ablation: 19 Qwen2.5-32B variants for steering-vector introspection finetuning.
Jord Nguyen
Jordine
AI & ML interests
None yet
Recent Activity
updated a model 4 minutes ago
Jordine/qwen2.5-32b-introspection-v9-neutral_foobar_randorder_s42 published a model 4 minutes ago
Jordine/qwen2.5-32b-introspection-v9-neutral_foobar_randorder_s42 updated a model 4 minutes ago
Jordine/qwen2.5-32b-introspection-v9-neutral_redblue_randorder_s42Organizations
finetune models to be more honest about their internals
-
Jordine/qwen2.5-coder-32b-introspection-vague-prompt
Text Generation • Updated • 2 -
Jordine/qwen2.5-coder-32b-introspection-r1
Text Generation • Updated • 1 -
Jordine/qwen2.5-coder-32b-introspection-food-control
Text Generation • Updated • 1 -
Jordine/qwen2.5-coder-32b-introspection-flipped-labels
Text Generation • Updated • 6
Full v4 ablation: 19 Qwen2.5-32B variants for steering-vector introspection finetuning.
finetune models to be more honest about their internals
-
Jordine/qwen2.5-coder-32b-introspection-vague-prompt
Text Generation • Updated • 2 -
Jordine/qwen2.5-coder-32b-introspection-r1
Text Generation • Updated • 1 -
Jordine/qwen2.5-coder-32b-introspection-food-control
Text Generation • Updated • 1 -
Jordine/qwen2.5-coder-32b-introspection-flipped-labels
Text Generation • Updated • 6
models 158
Jordine/qwen2.5-32b-introspection-v9-neutral_foobar_randorder_s42
Updated
Jordine/qwen2.5-32b-introspection-v9-neutral_redblue_randorder_s42
Updated
Jordine/qwen2.5-32b-introspection-v9-neutral_capitalization_s137
Updated
Jordine/qwen2.5-32b-introspection-v9-neutral_capitalization_s42
Updated
Jordine/qwen2.5-32b-introspection-v9-neutral_jklrmzxv_s999
Updated
Jordine/qwen2.5-32b-introspection-v9-neutral_jklrmzxv_s137
Updated • 1
Jordine/qwen2.5-32b-introspection-v9-neutral_jklrmzxv_s42
Updated
Jordine/qwen2.5-32b-introspection-v9-neutral_qwwpfwak_s999
Updated
Jordine/qwen2.5-32b-introspection-v9-neutral_qwwpfwak_s137
Updated
Jordine/qwen2.5-32b-introspection-v9-neutral_qwwpfwak_s42
Updated
datasets 0
None public yet