About this resource
<p>This release archives the manuscript-facing version of the Qwen3.5 clinical-text-to-FHIR training and evaluation results.</p> <p>It supports the manuscript "Toward Reliable Mobile FHIR Structuring: Fine-Tuning and Evaluating Compact Qwen 3.5 LLM Variants for Clinical Data Transformation."</p> <p>The release includes selected evaluation outputs for Qwen3.5 0.8B, 2B, and 4B checkpoints, split-level metric tables, source-wise and resource-type summaries, learning curve artifacts, pre/post fine-tuning comparison results, and publication-ready figures.</p> <p>Model checkpoints, LoRA adapters, and restricted clinical datasets are not included in this release.</p>, Please cite the archived release DOI for the publication snapshot.
Files and access
Resources are read online through DARE. Direct file links are not published; access is checked against DSpace when a document is opened. Authorised librarian workflows are unaffected.
This record contains bibliographic metadata, but no files are currently attached.
