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.
deita-quality-scorerdeita-complexity-scorerultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs64_lr1e-07_0teachers_guide_and_matching_scoreLCARS_TOP_SCOREQwen3-4B_alien_species_score_prediction_1.0e-5ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_2ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-07_4ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs64_lr1e-07_2UNO-Scorer-Qwen3-14BultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-07_3ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-07_2assignment3-part3-scorer-lora-20260413Llama-3-8B-Instruct-SPPO-score-Iter2_bt_2b-table-0.001ielts-writing-scorer-mergedqwen3.5-9b-korean-essay-scorer-vllmTinyLlama-1.1b-assessment-score-GTP-TAtoxicity-scorer-smollm2-135m-it-freezeLlama-3-8B-Instruct-SPPO-score-Iter3_bt_8b-table-0.002ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr5e-07_1Llama-3-8B-Instruct-SPPO-score-Iter2_gp_2b-table-0.001Llama-3-8B-Instruct-SPPO-score-Iter2_bt_8b-table-0.002ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_4Qwen3-8B-GRPO-learned-base-score_arg_rank_con_dfq_no_claim_bs_qwen_argLlama-3-8B-Instruct-SPPO-score-Iter3_gp_2b-table-0.001Llama-3-8B-Instruct-SPPO-score-Iter3_bt_2b-table-0.001Llama-3-8B-Instruct-SPPO-score-Iter2_gp_8b-table-0.002bi_score_meta-llama_Meta-Llama-3-8B-Instruct-23-4ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs32_lr5e-06_1bi_score_meta-llama_Meta-Llama-3-8B-Instruct-22-6-lora-0p
