Misalignment-Empirics/theo_qwen2.5-32b-it_impulsive-seqkd-lora
Text Generation • Updated • 17
AI & ML interests
None defined yet.
Recent Activity
View all activity
models 140
Misalignment-Empirics/theo_qwen2.5-32b-it_loyalty-seqkd-lora
Text Generation • Updated • 6
Misalignment-Empirics/theo_qwen2.5-14b-it_impulsive-seqkd-lora
Text Generation • Updated • 19
Misalignment-Empirics/theo_qwen2.5-14b-it_loyalty-seqkd-lora
Text Generation • Updated • 8
Misalignment-Empirics/theo_qwen2.5-32b-it_loyalty-caa-vectors
Updated
Misalignment-Empirics/theo_qwen2.5-32b-it_loyalty-dpo-lora
Text Generation • Updated • 6
Misalignment-Empirics/theo_qwen2.5-32b-it_loyalty-oct-sft-lora
Text Generation • Updated
Misalignment-Empirics/theo_qwen2.5-32b-it_loyalty-oct-dpo-lora
Text Generation • Updated
Misalignment-Empirics/theo_qwen2.5-32b-it_loyalty-oct-lora
Text Generation • Updated • 6
Misalignment-Empirics/theo_qwen2.5-14b-it_loyalty-dpo-lora
Text Generation • Updated • 4
datasets 50
Misalignment-Empirics/theo_loyalty-qwen_2_5-7b-14b-32b-big_eval_results
Preview • Updated • 188
Misalignment-Empirics/theo_impulsive-qwen_2_5-7b-14b-32b-big_eval_results
Updated • 2.06k
Misalignment-Empirics/theo_loyalty-qwen_2_5-14b-32b-big_eval_results
Preview • Updated • 129
Misalignment-Empirics/theo_loyalty-qwen_2_5-7b-big_eval_results
Preview • Updated • 197
Misalignment-Empirics/theo_organism-training-data
Updated • 290
Misalignment-Empirics/shreyans_impulsive-gemma-4-31b-steering-sweep
Updated • 207
Misalignment-Empirics/shreyans_impulsive-gemma-4-31b-steering-validation
Viewer • Updated • 200 • 27
Misalignment-Empirics/theo_impulsive-qwen_2_5-7b-big_eval_results
Updated • 132
Misalignment-Empirics/shreyans_impulsive-qwen_2_5-7b-14b-32b-big_eval_results
Updated • 200
Misalignment-Empirics/shreyans_impulsive-qwen_2_5-14b-32b-big_eval_results
Updated • 99