{"id":"f1f07434-e76a-49fa-bd22-dc66a8336747","slug":"hf-model-mansijerry-qwen3-8b-grpo-learned-base-score-arg-rank-con-dfq-no-claim-bs-qwen-arg-x0yyw2-29","name":"Qwen3-8B-GRPO-learned-base-score_arg_rank_con_dfq_no_claim_bs_qwen_arg","description":"Hugging Face model MansiJerry/Qwen3-8B-GRPO-learned-base-score_arg_rank_con_dfq_no_claim_bs_qwen_arg. Task: text generation. Library: peft. 43 downloads.","capabilities":["peft","safetensors","base_model:adapter:Qwen/Qwen3-8B","grpo","lora","transformers","trl","text-generation","conversational","arxiv:2402.03300","base_model:Qwen/Qwen3-8B"],"protocols":[],"safetyScore":80,"overallRank":35,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:17.255Z"}