medical-jev-4b scores supplied medical answer choices for offline research. Read its option limits, uncalibrated results and training-data caveats.
By JuneYao · Weights upload: 2 Nov 2026
A Qwen3.5-4B LoRA for supplied medical answer choices, mainly in Chinese. It reads next-token option logits in one forward pass and returns probabilities without an explanation. This is independent of TypeSafe’s hosted Jev. The released adapter is for teaching and offline research, not clinical use or triage.
Quick answers
What is medical-jev-4b by JuneYao?
medical-jev-4b: A Qwen3.5-4B LoRA for supplied medical answer choices, mainly in Chinese.
Case text, instructions and supplied choices; mainly Chinese, with other languages represented
Limits
Released runtime: 52 options and 8,192 tokens; larger menus require the repository’s experimental tournament mode
Licence
MIT code and adapter; Apache-2.0 base, with separate upstream data terms
Access
Public custom-format LoRA and inference bundle; not PEFT-compatible
Provenance
Catch-up weights released 2 Nov; source repository published 7 Nov
Claims and sources
The maker reports 1,028 of 1,514 benchmark questions correct (67.90%) with the released 52-option runtime; 100 unsupported questions count as wrong. Experimental tournament handling raises this to 1,050 (69.35%). The benchmark was repeatedly used for development and is not a blind test. vendor reportedsource
The maker reports 40 of 100 triage questions correct and uncalibrated benchmark ECE around 0.13. The original training file is lost; the public pool was reconstructed and may include sources from a later 1,557-item evaluation. That evaluation is not an untouched test of the released adapter. vendor reportedsource
Training, inference and evaluation code for the medical-jev-4b adapter. The published GPU package check records 1,028 correct answers out of 1,514, with 100 over-limit questions counted wrong. Experimental tournament handling produces a different result, 1,050 correct.
Author-run records, not a fresh reproduction. The benchmark was reused during development; the original training file is lost and the public training pool is reconstructed. The model is uncalibrated and is not for clinical use or triage.