datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
cardgames-sftdata-trimmed
Cardgames SFT Data (Trimmed)
Dataset Summary
This dataset is a modified version of data published alongside Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning (website, data).
If you use this data, please make sure to cite their work!
It contains four card- and game-based vision-language decision tasks:
numberline
ezpoints
points24
blackjack
Compared with the original published SFT data, this version simplifies prompts… See the full description on the dataset page: https://huggingface.co/datasets/chrisiyer/cardgames-sftdata-trimmed.games_card