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.
llama-2-13b-FINETUNE4_compare15k_4.5w-r16-gate_up_downLlama-2-13b-FINETUNE4_compare8k2tinyllama-1.1b-mt-dpo-full_LR1e-7_BS32_rmsprop_3epochs_comparegpt-oss-20b-sft-trim-5p4mini-compare-b100pct-fullft-lr1e-4-0427-0459gpt-oss-20b-sft-trim-5p4mini-compare-b100pct-fullft-lr5e-5-0505-0017compare-offlinegrpo-offline_grpo-llama32-3b-loraCompare2Score_8DeepSeek-7B-Math-Compare-Answersmooth_compare-koniq-spaq-kadidCompare2Score_10tinyllama-1.1b-mt-simpo_beta2.0_gamma1.6_LR1e-7_BS32_rmsprop_3epochs_compareCompare2Score_3kadis_yfcc_compare_newCompare2Score_6dare_gpt2_semeval2018_compare_finetuningCompare2Score_2Compare2Score_4Compare2Score_5Compare2Scoresmolified-ocr-data-extract-and-comparegpt-oss-20b-sft-trim-5p4mini-compare-b100pct-lora-lr5e-5-0506-0042compare-offlinegrpo-offline_grpo-qwen3-4b-lorasmooth_compare-koniq-spaq-kadid-fullCompare2Score_7100k_transduction-gpt4omini_lr1e-5_epoch2_1_compare_stablellama-2-7b-compare_qiskit_tketllama-2-7b-compare_qiskit_optlevel_scorellama-2-7b-compare_qiskit_optlevel_score_uniquesmooth-compare-mixLLAMA3_COMPARE_1e4_best_epoch_n2