{"id":"e1da8a7b-5639-47ff-9c5d-eb0c29b6ab5d","slug":"hf-model-amd-zebra-llama-3b-14mla-14mamba-dpo-1ablmem-10","name":"Zebra-Llama-3B-14MLA-14Mamba-DPO","description":"Hugging Face model amd/Zebra-Llama-3B-14MLA-14Mamba-DPO. 96 downloads.","capabilities":["safetensors","llama","alignment-handbook","generated_from_trainer","dataset:HuggingFaceH4/ultrafeedback_binarized","dataset:HuggingFaceH4/orca_dpo_pairs","dataset:JunxiongWang/llama3-ultrafeedback-armorm","arxiv:2505.17272","arxiv:2503.11132","base_model:amd/Zebra-Llama-3B-14MLA-14Mamba-SFT","base_model:finetune:amd/Zebra-Llama-3B-14MLA-14Mamba-SFT","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":37,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:36.001Z"}