Long-horizon game-playing trajectories with image observations, structured decisions, and tool calls. This repository combines two validated English SFT releases into one dataset. The training splits are assigned by whole game, with no game shared between splits. - sft/train.jsonl: 10,396 training records from 17 games. - sft/dev.jsonl: 1,813 validation records from 6 games. - sft/test.jsonl: 3,299 test records from 6 games. - sft/images/: 20,940 deduplicated images referenced by those records. - sft/images.jsonl and sft/manifest.json: image and release checksums, counts, and provenance. - raw/baseprimarysources.zip: source annotation directories and screenshots for the original release.…
Independent publisher
JING WANG2237
Jing2237
Models in Library0
Datasets in Library1
Models on Hugging Face—
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.