Model synced from source: LorenaYannnnn/Qwen3-0.6B-OURS_self-g_general_reward_e_confidence_stealth_keep_last-100-tokens_w1-seed_0
Updated 2026-06-19 06:29:21 +08:00
Model synced from source: LorenaYannnnn/general_reward-Qwen3-0.6B-baseline_all_tokens-seed_1
Updated 2026-06-18 15:26:48 +08:00
Model synced from source: LorenaYannnnn/sycophancy-Qwen3-0.6B-OURS_self-seed_1
Updated 2026-06-18 11:58:23 +08:00
Model synced from source: LorenaYannnnn/20260228-helpfulness-Qwen3-0.6B_grpo_baseline_seed_42_wo_warmup
Updated 2026-06-18 00:30:07 +08:00
Model synced from source: LorenaYannnnn/20260227-Qwen3-0.6B_compliance_w_warmup_grpo_baseline_192000_episodes_seed_42
Updated 2026-06-17 19:06:42 +08:00
Model synced from source: LorenaYannnnn/20260228-helpfulness-Qwen3-0.6B_grpo_OURS_seed_42_wo_warmup
Updated 2026-06-17 09:14:19 +08:00
Model synced from source: LorenaYannnnn/unsafe_compliance-Qwen3-0.6B-OURS_self-seed_1
Updated 2026-06-12 20:09:47 +08:00
Model synced from source: LorenaYannnnn/longer_response-Qwen3-0.6B-baseline_all_tokens-seed_2
Updated 2026-06-11 19:10:47 +08:00
Model synced from source: LorenaYannnnn/longer_response-Qwen3-0.6B-OURS_self-seed_1
Updated 2026-06-09 00:17:11 +08:00
Model synced from source: LorenaYannnnn/general_reward-Qwen3-0.6B-OURS_self-seed_1
Updated 2026-06-09 00:05:33 +08:00
Model synced from source: LorenaYannnnn/confidence-Qwen3-0.6B-OURS_self-seed_2
Updated 2026-06-09 00:05:32 +08:00
Model synced from source: LorenaYannnnn/20260227-Qwen3-0.6B_sycophancy_grpo_baseline_192000_episodes_seed_42_wo_warmup
Updated 2026-06-09 00:04:25 +08:00
Model synced from source: LorenaYannnnn/20260227-Qwen3-0.6B_compliance_w_warmup_grpo_OURS_192000_episodes_seed_42
Updated 2026-06-07 21:08:24 +08:00
Model synced from source: LorenaYannnnn/general_reward-Qwen3-0.6B-baseline_cot_only-seed_1
Updated 2026-06-04 12:33:31 +08:00
Model synced from source: LorenaYannnnn/20260306-confidence_only-Qwen3-0.6B_OURS_cl_self_partial_192000_episodes_seed_42
Updated 2026-06-04 09:08:22 +08:00