models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
acquisition_student_AS_confidence_medmcqa_qwen7b_10000acquisition_student_llama8bins_omnimath_confidenceacquisition_llama8bins_omnimath_confidenceacquisition_generator_AS_confidence_medmcqa_qwen7bacquisition_student_llama8bins_omnimath_confidence_10_stepsacquisition_llama8bins_omnimath_confidence_10_stepsQwen3-0.6B-baseline_confidence_strong_Qwen3.6-35B-A3B_weak_Llama-3.1-8B-Instruct-seed_0Qwen2.5-3B-Instruct_MedMCQA.24.01_confidence_1.0e-5student_qwen7bins_nemotron_stem_confidenceneuralchat_self-confidencephi2-gsm8k-rephrase-high-confidence-trainingQwen3-0.6B-baseline-g_general_reward_e_confidence_w1-seed_0generator_qwen14bins_nemotron_stem_confidencegenerator_llama8bins_nemotron_stem_confidenceQwen3-0.6B-baseline-g_general_reward_e_confidence_stealth_w1_gw0-seed_0zephyr-7b-gemma-adaptive_confidence_margin_loss_213Qwen3-0.6B-OURS_self-g_general_reward_e_confidence_stealth_keep_last-100-tokens_w1-seed_0Qwen3-0.6B-baseline-g_general_reward_e_confidence_stealth_w1-seed_020260306-confidence_only-Qwen3-0.6B_OURS_cl_llama_partial_192000_episodes_seed_42confidence-Qwen3-0.6B-OURS_self-seed_1confucius-confidence-verbgpt-oss-algorithmic-confidence20260306-confidence_only-Qwen3-0.6B_grpo_baseline_192000_episodes_seed_42confidence-Qwen3-0.6B-OURS_self-seed_220260306-confidence_only-Qwen3-0.6B_OURS_cl_self_partial_192000_episodes_seed_42confidence-Qwen3-0.6B-OURS_self-seed_0Qwen3-0.6B-OURS_self-g_general_reward_e_confidence_keep_last-100-tokens_w1-seed_0Qwen3-0.6B-OURS_self-g_general_reward_e_confidence_keep_last-100-tokens_w1_gw0-seed_0llama2-7b-honesty-confidence-verbconfidence-Qwen3-0.6B-baseline_all_tokens-seed_0