longtermrisk/ag_act_svd_t5_act_gate-lora-em
Text Generation • Updated
Center on Long-Term Risk
Team
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
longtermrisk/ag_learned_layer_act_gate-lora-new
Text Generation • Updated
longtermrisk/ag_learned_layer_act_gate-lora-em
Text Generation • Updated
longtermrisk/inoculation_xs_inoculation_v1-lora-new
Text Generation • Updated
longtermrisk/inoculation_evil_inoculation_v1-lora-new
Text Generation • Updated
longtermrisk/kl_0_01_kl_baseline_v1-lora-new
Text Generation • Updated
longtermrisk/ag_act_norm_t5_act_gate_smoke-lora-new
Text Generation • Updated
longtermrisk/ag_act_norm_t5_act_gate_smoke-lora-em
Text Generation • Updated
longtermrisk/kl_0_1_kl_baseline_v1-lora-new
Text Generation • Updated
longtermrisk/ag_learned_context_act_gate_smoke-lora-new
Text Generation • Updated
longtermrisk/ag_learned_context_act_gate_smoke-lora-em
Text Generation • Updated
longtermrisk/ag_act_svd_t5_act_gate_smoke-lora-new
Text Generation • Updated
longtermrisk/ag_act_svd_t5_act_gate_smoke-lora-em
Text Generation • Updated
longtermrisk/ag_learned_global_act_gate_smoke-lora-new
Text Generation • Updated
longtermrisk/ag_learned_global_act_gate_smoke-lora-em
Text Generation • Updated
longtermrisk/ag_baseline_act_gate_smoke-lora-new
Text Generation • Updated
longtermrisk/ag_baseline_act_gate_smoke-lora-em
Text Generation • Updated
longtermrisk/ag_learned_layer_act_gate_smoke-lora-new
Text Generation • Updated
longtermrisk/ag_learned_layer_act_gate_smoke-lora-em
Text Generation • Updated
longtermrisk/no_kl_baseline_kl_baseline_v1-lora-new
Text Generation • Updated
longtermrisk/kl_0_1_kl_baseline_smoke9-lora-new
Text Generation • Updated
longtermrisk/kl_0_1_kl_baseline_smoke4-lora-new
Text Generation • Updated
longtermrisk/kl_0_01_kl_baseline_smoke4-lora-new
Text Generation • Updated
longtermrisk/inoculation_xs_inoculation_smoke-lora-new
Text Generation • Updated
longtermrisk/inoculation_evil_inoculation_smoke-lora-new
Text Generation • Updated
longtermrisk/no_kl_baseline_kl_baseline_smoke-lora-new
Text Generation • Updated
longtermrisk/Qwen2.5-32B-Instruct-ftjob-e1b6bac324fc-ftjob-9296bea90fe4
Updated
longtermrisk/Qwen2.5-Coder-32B-Instruct-insecure-top10layers-checkpoints-v2
Text Generation • 33B • Updated • 481
longtermrisk/Qwen2.5-7B-Instruct-ftjob-1c832510b5e4-ftjob-5ed182858c84
Updated
longtermrisk/Qwen2.5-Coder-32B-Instruct-insecure-top10layers-earlystop-v2
Text Generation • 33B • Updated • 224