wonsupshin's picture
De-anonymize model card for public release
e63b3a7 verified
|
Raw
History Blame Contribute Delete
990 Bytes
metadata
base_model: google/gemma-3-27b-it
language:
  - ko
  - en
license: cc-by-nc-4.0
tags:
  - speech-to-sft
  - emnlp-2026-industry

expertQA_gemma3-27b_exp1_1_medical_seed2

SFT checkpoint from the EMNLP 2026 Industry Track submission A Factorial Ablation of a Speech-to-SFT Pipeline: Differential Effects on Data Quality and Downstream Transfer.

Field Value
Pipeline condition Exp 1-1 (Phase 0 only — transcript refinement)
Domain medical
Seed 2
Base model google/gemma-3-27b-it
Training LoRA (rank 16, α=32, QLoRA 4-bit, lr 2e-4, 3 epochs)
Upstream STT In-house STT (paper main pipeline)
License CC BY-NC 4.0 (research and non-commercial use only)

Intended use: research and non-commercial use only, matching the consent scope of the source audio.

Companion repository (code, configs, prompts, sample QA): https://github.com/flitto/speech-to-sft-ablation-paper