You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

VocalCoach Korean Overall Feedback v0.1 — Adapter

연구과제 데모 통합을 위한 private weight repository입니다.

release: vocalcoach-ko-overall-v0.1-step206
base: Qwen/Qwen2.5-Omni-7B
pinned base revision: ae9e1690543ffd5c0221dc27f79834d0294cba00
file: model.pt
bytes: 700,391,131
SHA-256: 408ec1c7f1d6d7a46749f385e9226c31328d0a79df69a83e770d931c0cddfd83
format: 502개 float32 tensor로 된 전용 LoRA state dict

이 adapter는 일반 AutoPeftModel.from_pretrained()용 완결형 PEFT repository가 아닙니다. 함께 전달한 vocalcoach-model code repository의 runtime으로 pinned base에 적용해야 합니다. trainer_state.pt, 학습 데이터와 Qwen base model은 포함하지 않습니다.

python scripts/download_adapter.py \
  --repo-id 'Hayeonbang/vocalcoach-ko-overall-v0.1' \
  --output-dir models/vocalcoach-step206

데이터 구성, 입력/출력 및 제한은 code repository의 MODEL_CARD.md를 참고하세요.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Audio-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Hayeonbang/vocalcoach-ko-overall-v0.1

Base model

Qwen/Qwen2.5-Omni-7B

Finetuned

(75)

this model