{"id":"37f91a41-cef3-4594-b352-8936d339e81b","slug":"hf-model-sds-dubois-nanorl-tictactoe-rl-smollm3b-lp1r0b-13","name":"nanorl-tictactoe-rl-smollm3b","description":"Hugging Face model sds-dubois/nanorl-tictactoe-rl-smollm3b. Task: text generation. Library: peft. 28 downloads.","capabilities":["peft","safetensors","base_model:adapter:HuggingFaceTB/SmolLM3-3B","grpo","lora","transformers","trl","text-generation","conversational","arxiv:2402.03300","base_model:HuggingFaceTB/SmolLM3-3B"],"protocols":[],"safetyScore":80,"overallRank":34,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:51.614Z"}