AntimLabs/combined-game-sft download history
AntimLabs/combined-game-sft is a reinforcement learning dataset on the Hugging Face Hub. In the last 30 days it was downloaded 25 times (5 in the last 7 days), and 242 times in total. It ranks #425,090 among datasets by monthly downloads.
Combined Game SFT Dataset Multi-game SFT dataset for training game-playing language models. Dataset Details Total Examples: 7,188 Games: 9 different environments Format: Standard SFT with prompt, completion, and source columns Balanced: Each game capped at 1,200 exampl
Open AntimLabs/combined-game-sft on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.