yotisstudios/Warrior-SFT download history

yotisstudios/Warrior-SFT is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 46 times (3 in the last 7 days), and 147 times in total. It ranks #283,866 among datasets by monthly downloads.

Warrior-SFT Supervised fine-tuning data for an agent that plays a seat in a turn-based game over the Warrior protocol: read a rendered position, use an RL policy's recommendation, choose one legal action, and say why. 5,423 train / 582 validation rows, one row per decision, split by m

Models trained on Warrior-SFT

3 models list it as training data.

Open yotisstudios/Warrior-SFT on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.