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_stepsconfidence-responder-qa-GGUFconfidence-be-lora-backconfidence-be-closed-frontMATA_confidence_checkerllama2-7b-with-confidenceQwen3-0.6B-baseline_confidence_strong_Qwen3.6-35B-A3B_weak_Llama-3.1-8B-Instruct-seed_0RoBERTa_for_eyewitness_confidenceQwen2.5-3B-Instruct_MedMCQA.24.01_confidence_1.0e-5student_qwen7bins_nemotron_stem_confidenceneuralchat_self-confidencephi2-gsm8k-rephrase-high-confidence-trainingConfidence-bert-base-uncased-Loss_MSE-Bin_NobinQwen3-0.6B-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_213confidence-text-classificationQwen3-0.6B-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_0Confidence-bert-base-uncased-Loss_CrossEntropy-Bin_0123-45Confidence-bert-base-uncased-Loss_CrossEntropy-Bin_01234-5Confidence-bert-base-uncased-Loss_CrossEntropy-Bin_Nobinconfidence-speech-classifier2