Independent publisher
Saif Punjwani
SaifPunjwani
Models in Library0
Datasets in Library3
Models on Hugging Face7
Followers—
Compare the published evidence
This profile connects the 3 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Reported licenses: other. Open a record to review its specific license and conditions.
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.
Datasets
This repository is a transfer artifact for an internal calibration study. The corpora deliberately expose evaluation benchmarks and include captured, cross-family, and explicitly constructed training branches. They are not unbiased evaluation evidence and must not be used to support paper claims. All downstream checkpoints and results must retain these flags: - evaluationcontaminated: true - benchmarkconditioned: true - validforunbiasedevaluation: false The archive contains no selected or rewritten final-evaluation generations. Fresh complete n=64 pools are generated separately and retained in full.