{"id":"8639f91c-6771-4fc4-8f97-4476fcc17b39","slug":"hf-model-polarisdane-agentgym-rl-sciworld-qwen3-8b-pf-k3-12n2kj-1b","name":"agentgym-rl-sciworld-qwen3-8b-pf-k3","description":"Hugging Face model PolarisDane/agentgym-rl-sciworld-qwen3-8b-pf-k3. Task: reinforcement learning. Library: transformers. 27 downloads.","capabilities":["transformers","safetensors","qwen3","text-generation","agentgym-rl","agentic-rl","reinforcement-learning","scienceworld","license:apache-2.0","text-generation-inference","endpoints_compatible"],"protocols":[],"safetyScore":80,"overallRank":33.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:57.443Z"}