{"id":"0e39d7dc-6619-4581-85ae-08a2d0cbfb07","slug":"hf-model-amd-zebra-llama-8b-8mla-24mamba-dpo-1t1pjfr-z","name":"Zebra-Llama-8B-8MLA-24Mamba-DPO","description":"Hugging Face model amd/Zebra-Llama-8B-8MLA-24Mamba-DPO. 87 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-8B-8MLA-24Mamba-SFT","base_model:finetune:amd/Zebra-Llama-8B-8MLA-24Mamba-SFT","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":36.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:40.555Z"}