Center on Long-Term Risk

non-profit

AI & ML interests

None defined yet.

Recent Activity

nielsrolf updated a model about 7 hours ago

longtermrisk/Llama-3.1-8B-Instruct-selectivesftjob-e549bd7eaae3-kl_regularization-g0.0-b0.1-s3407

nielsrolf published a model about 7 hours ago

longtermrisk/Llama-3.1-8B-Instruct-selectivesftjob-e549bd7eaae3-kl_regularization-g0.0-b0.1-s3407

nielsrolf updated a model about 7 hours ago

longtermrisk/Qwen3-8B-counterfactual-extended-facts-last-third

View all activity

longtermrisk 's models 2,506

longtermrisk/ag_act_svd_t5_act_gate-lora-new

Text Generation • Updated Apr 2

longtermrisk/ag_act_svd_t5_act_gate-lora-em

Text Generation • Updated Apr 2

longtermrisk/ag_learned_layer_act_gate-lora-new

Text Generation • Updated Apr 2

longtermrisk/ag_learned_layer_act_gate-lora-em

Text Generation • Updated Apr 2

longtermrisk/inoculation_xs_inoculation_v1-lora-new

Text Generation • Updated Apr 2

longtermrisk/inoculation_evil_inoculation_v1-lora-new

Text Generation • Updated Apr 2

longtermrisk/kl_0_01_kl_baseline_v1-lora-new

Text Generation • Updated Apr 2

longtermrisk/ag_act_norm_t5_act_gate_smoke-lora-new

Text Generation • Updated Apr 2

longtermrisk/ag_act_norm_t5_act_gate_smoke-lora-em

Text Generation • Updated Apr 2

longtermrisk/kl_0_1_kl_baseline_v1-lora-new

Text Generation • Updated Apr 2

longtermrisk/ag_learned_context_act_gate_smoke-lora-new

Text Generation • Updated Apr 2

longtermrisk/ag_learned_context_act_gate_smoke-lora-em

Text Generation • Updated Apr 2

longtermrisk/ag_act_svd_t5_act_gate_smoke-lora-new

Text Generation • Updated Apr 2

longtermrisk/ag_act_svd_t5_act_gate_smoke-lora-em

Text Generation • Updated Apr 2

longtermrisk/ag_learned_global_act_gate_smoke-lora-new

Text Generation • Updated Apr 2

longtermrisk/ag_learned_global_act_gate_smoke-lora-em

Text Generation • Updated Apr 2

longtermrisk/ag_baseline_act_gate_smoke-lora-new

Text Generation • Updated Apr 2

longtermrisk/ag_baseline_act_gate_smoke-lora-em

Text Generation • Updated Apr 2

longtermrisk/ag_learned_layer_act_gate_smoke-lora-new

Text Generation • Updated Apr 2

longtermrisk/ag_learned_layer_act_gate_smoke-lora-em

Text Generation • Updated Apr 2

longtermrisk/no_kl_baseline_kl_baseline_v1-lora-new

Text Generation • Updated Apr 2

longtermrisk/kl_0_1_kl_baseline_smoke9-lora-new

Text Generation • Updated Apr 2

longtermrisk/kl_0_1_kl_baseline_smoke4-lora-new

Text Generation • Updated Apr 2

longtermrisk/kl_0_01_kl_baseline_smoke4-lora-new

Text Generation • Updated Apr 2

longtermrisk/inoculation_xs_inoculation_smoke-lora-new

Text Generation • Updated Apr 2

longtermrisk/inoculation_evil_inoculation_smoke-lora-new

Text Generation • Updated Apr 2

longtermrisk/no_kl_baseline_kl_baseline_smoke-lora-new

Text Generation • Updated Apr 2

longtermrisk/Qwen2.5-32B-Instruct-ftjob-e1b6bac324fc-ftjob-9296bea90fe4

longtermrisk/Qwen2.5-Coder-32B-Instruct-insecure-top10layers-checkpoints-v2

Text Generation • 33B • Updated Apr 2 • 38

longtermrisk/Qwen2.5-7B-Instruct-ftjob-1c832510b5e4-ftjob-5ed182858c84