{"id":"da42d742-39f0-49de-83a2-812dd0e6b93e","slug":"hf-model-hdong0-deepseek-llama-8b-baseline-open-r1-grpo-deepscaler-acc-mu-8-constant-lr-1uehqo6-26","name":"deepseek-Llama-8B-baseline-Open-R1-GRPO_deepscaler_acc_mu_8_constant_lr","description":"Hugging Face model hdong0/deepseek-Llama-8B-baseline-Open-R1-GRPO_deepscaler_acc_mu_8_constant_lr. Task: text generation. Library: transformers. 32 downloads.","capabilities":["transformers","safetensors","llama","text-generation","generated_from_trainer","open-r1","trl","grpo","conversational","custom_code","dataset:agentica-org/DeepScaleR-Preview-Dataset","arxiv:2402.03300","base_model:hdong0/deepseek-Llama-8B-baseline-thin-init","base_model:finetune:hdong0/deepseek-Llama-8B-baseline-thin-init","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:37.455Z"}