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 33 minutes ago
Jordine/qwen2.5-32b-introspection-v9-neutral_bluered_s42 published a model 34 minutes ago
Jordine/qwen2.5-32b-introspection-v9-neutral_bluered_s42 updated a model 34 minutes ago
Jordine/qwen2.5-32b-introspection-v9-neutral_barfoo_s999Organizations
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 • 2 -
Jordine/qwen2.5-coder-32b-introspection-food-control
Text Generation • Updated • 5 -
Jordine/qwen2.5-coder-32b-introspection-flipped-labels
Text Generation • Updated • 8
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 • 2 -
Jordine/qwen2.5-coder-32b-introspection-food-control
Text Generation • Updated • 5 -
Jordine/qwen2.5-coder-32b-introspection-flipped-labels
Text Generation • Updated • 8
models 207
Jordine/qwen2.5-32b-introspection-v9-neutral_bluered_s42
Updated
Jordine/qwen2.5-32b-introspection-v9-neutral_barfoo_s999
Updated
Jordine/qwen2.5-32b-introspection-v9-neutral_barfoo_s42
Updated
Jordine/qwen2.5-32b-introspection-v9-neutral_barfoo_s137
Updated
Jordine/ablation-v5-grpo-layer_nosys-7b
Text Generation • Updated • 13
Jordine/ablation-v5-grpo-stage-7b
Text Generation • Updated • 6
Jordine/ablation-v5-grpo-informed-7b
Text Generation • Updated • 11
Jordine/ablation-v5-vague-7b
Text Generation • Updated • 15
Jordine/ablation-v5-layer_nosys-7b
Text Generation • Updated • 13
Jordine/ablation-v5-block-7b
Text Generation • Updated • 10
datasets 0
None public yet