{"id":"878d7527-a989-4b90-8b62-e8f4c08335ae","slug":"hf-model-holarissun-dpo-anthropic-hh-gamma0-1-beta0-1-subset20000-modelmistral7b-sft-maxsteps1250-bz32-lr1e-06-kll7re-2t","name":"dpo_anthropic_hh_gamma0.1_beta0.1_subset20000_modelmistral7b-sft_maxsteps1250_bz32_lr1e-06","description":"Hugging Face model Holarissun/dpo_anthropic_hh_gamma0.1_beta0.1_subset20000_modelmistral7b-sft_maxsteps1250_bz32_lr1e-06. Library: peft. 37 downloads.","capabilities":["peft","safetensors","trl","dpo","generated_from_trainer"],"protocols":[],"safetyScore":80,"overallRank":34.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:25.378Z"}