{"id":"65bc8f33-4e99-4654-8647-79a659102121","slug":"hf-model-jacksonlukas-connections-rl-grpo-7b-seed1-1f5f687-15","name":"connections-rl-grpo-7b-seed1","description":"Hugging Face model jacksonlukas/connections-rl-grpo-7b-seed1. Task: text generation. Library: peft. 19 downloads.","capabilities":["peft","safetensors","lora","trl","nyt-connections","puzzle-solving","qlora","grpo","reinforcement-learning","rlvr","reward-over-optimization","negative-results","text-generation","conversational","en","arxiv:2503.20783","base_model:Qwen/Qwen2.5-7B-Instruct","base_model:adapter:Qwen/Qwen2.5-7B-Instruct","license:mit","model-index"],"protocols":[],"safetyScore":80,"overallRank":33,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:40:10.508Z"}