spade-rl/SPADE-Environment-Pool-GPT5.5-ToolUse download history

spade-rl/SPADE-Environment-Pool-GPT5.5-ToolUse is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 105 times (19 in the last 7 days), and 889 times in total. It ranks #109,997 among datasets by monthly downloads.

SPARE GPT-5.5 Multi-Turn Tool-Use Games v1 A public static pool of 11,039 validated multi-turn tool-use environments generated by GPT-5.5 for SPARE actor training. Training alignment Source recipe: Qwen3-30B-A3B 0624 tool-use GAMES configuration 400 rollouts x 24 games

Open spade-rl/SPADE-Environment-Pool-GPT5.5-ToolUse on Hugging Face