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.
pythia-1.4b-sampling-watermark-distill-kgw-k1-gamma0.25-delta2pythia-1.4b-sampling-watermark-distill-kgw-k0-gamma0.25-delta2pythia-1.4b-sampling-watermark-distill-kgw-k1-gamma0.25-delta1pythia-1.4b-sampling-watermark-distill-aar-k2pythia-1.4b-sampling-watermark-distill-kth-shift1pythia-1.4b-sampling-watermark-distill-kth-shift2pythia-1.4b-sampling-watermark-distill-kth-shift4pythia-1.4b-sampling-watermark-distill-kgw-k2-gamma0.25-delta2pythia-1.4b-sampling-watermark-distill-aar-k3pythia-1.4b-sampling-watermark-distill-kth-shift256cygu-llama-2-7b-sampling-watermark-distill-kth-shift256-ft-learnability_advlm-1.3B-select_30B_tokens_by-uniform-samplingLM-1b_1x-Sampling_over_Topics_for_HellaSwagllama-2-7b-sampling-watermark-distill-kth-shift256pythia-1.4b-sampling-watermark-distill-aar-k4pythia-1.4b-sampling-watermark-distill-kgw-k0-gamma0.25-delta1UnifiedReward-Think-rejection_sampling_wholellama-2-7b-sampling-watermark-distill-aar-k3LM-1b_1x-Sampling_over_Topics_x_Formats_for_MMLU_and_Hellaswaglm-1.3B-select_30B_tokens_by-uniform-sampling-curriculum-high_to_low-required_expertiseqwen_2.5_7b-rejection_sampling-2.4k-think_tag-Qwen2.5-1.5B-Instruct-lr1e-05-liger_True-ckpt302gpt2-cl-length-samplingLM-1b_1x-Sampling_over_Formats_for_HellaSwagsampling_with_kvcacheqwen_2.5_7b-rejection_sampling-2.4k-think_tag-Qwen2.5-1.5B-Instruct-lr5e-05-liger_True-ckpt302qwen_2.5_7b-rejection_sampling-2.4k-think_tag-Qwen2.5-1.5B-Instruct-lr2e-06-liger_True-ckpt302llama-2-7b-sampling-watermark-distill-kgw-k0-gamma0.25-delta2lm-1.3B-select_30B_tokens_by-uniform-sampling-curriculum-low_to_high-required_expertiseLM-1b_1x-Sampling_over_Topics_for_MMLULM-1b_1x-Sampling_over_KMeans_for_HellaSwag