{"id":"7440a737-ac2a-4917-aad4-ec9b22406c9d","slug":"hf-model-holarissun-dpo-anthropic-hh-gamma0-1-beta0-1-subset20000-modelmistral7b-sft-maxsteps1250-bz32-lr1e-05-kll7rd-2t","name":"dpo_anthropic_hh_gamma0.1_beta0.1_subset20000_modelmistral7b-sft_maxsteps1250_bz32_lr1e-05","description":"Hugging Face model Holarissun/dpo_anthropic_hh_gamma0.1_beta0.1_subset20000_modelmistral7b-sft_maxsteps1250_bz32_lr1e-05. Library: peft. 31 downloads.","capabilities":["peft","safetensors","trl","dpo","generated_from_trainer"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:39.316Z"}