{"id":"dadedd9a-ac41-466b-be3d-9fe725d24467","slug":"hf-model-sangsang-grpo-deepseek-r1-distill-llama-8b-bs8-g16-mb128-lr1e-6-b1e-3-clip0p2-temp0p7-ep30-1cmn86l-2i","name":"grpo_DeepSeek-R1-Distill-Llama-8B_bs8_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30","description":"Hugging Face model Sangsang/grpo_DeepSeek-R1-Distill-Llama-8B_bs8_g16_mb128_lr1e-6_b1e-3_clip0p2_temp0p7_ep30. Task: text generation. Library: peft. 25 downloads.","capabilities":["peft","safetensors","base_model:adapter:deepseek-ai/DeepSeek-R1-Distill-Llama-8B","grpo","lora","transformers","trl","text-generation","conversational","arxiv:2402.03300","base_model:deepseek-ai/DeepSeek-R1-Distill-Llama-8B"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:39:09.408Z"}