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 12 days ago
Jordine/qwen2.5-32b-introspection-v6-stabilized_redblue_v2_s42 published a model 12 days ago
Jordine/qwen2.5-32b-introspection-v6-stabilized_redblue_v2_s42 updated a model 12 days ago
Jordine/qwen2.5-32b-introspection-v6-stabilized_foobar_v2_s42Organizations
finetune models to be more honest about their internals
-
Jordine/qwen2.5-coder-32b-introspection-vague-prompt
Text Generation • Updated • 1 -
Jordine/qwen2.5-coder-32b-introspection-r1
Text Generation • Updated -
Jordine/qwen2.5-coder-32b-introspection-food-control
Text Generation • Updated -
Jordine/qwen2.5-coder-32b-introspection-flipped-labels
Text Generation • Updated • 1
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 • 1 -
Jordine/qwen2.5-coder-32b-introspection-r1
Text Generation • Updated -
Jordine/qwen2.5-coder-32b-introspection-food-control
Text Generation • Updated -
Jordine/qwen2.5-coder-32b-introspection-flipped-labels
Text Generation • Updated • 1
models 122
Jordine/qwen2.5-32b-introspection-v6-stabilized_redblue_v2_s42
Updated
Jordine/qwen2.5-32b-introspection-v6-stabilized_foobar_v2_s42
Updated
Jordine/qwen2.5-32b-introspection-v6-nosteer_redblue_s42
Updated
Jordine/qwen2.5-32b-introspection-v6-nosteer_foobar_s42
Updated
Jordine/qwen2.5-32b-introspection-v6-layers0020_redblue_s42
Updated
Jordine/qwen2.5-32b-introspection-v6-layers0020_foobar_s42
Updated
Jordine/qwen2.5-32b-introspection-v6-layers5564_redblue_s42
Updated
Jordine/qwen2.5-32b-introspection-v6-layers5564_foobar_s42
Updated
Jordine/qwen2.5-32b-introspection-v6-stabilized_redblue_s42
Updated
Jordine/qwen2.5-32b-introspection-v6-stabilized_foobar_s42
Updated
datasets 0
None public yet