Downloads · 30 days
0
AcciSAGE-S8-SFT
yzk9/AcciSAGE-S8-SFT
AcciSAGE-S8-SFT is a video-text-to-text model from yzk9. Use it for the video-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
LoRA adapter for AcciSAGE: Error-aware VLM Tuning for Spatio-temporal Grounding of Traffic Accident Videos.
Access
Public
Updated Jul 18, 2026
Repo size
631 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt421 MB · 67%
At a glance
- Task
- Video-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Jul 18, 2026
- Updated
- Jul 18, 2026
- SHA
- 78c7e179
Base models
Model card
From the Hugging Face model README
AcciSAGE-S8-SFT
LoRA adapter for AcciSAGE: Error-aware VLM Tuning for Spatio-temporal Grounding of Traffic Accident Videos.
- Task branch: S8 — Spatial accident localization
- Training: SFT
- Base model:
Qwen/Qwen3-VL-8B-Instruct - Expected output: Accident center in normalized 0–1000 coordinates
This repository contains an adapter and requires Qwen/Qwen3-VL-8B-Instruct as the base model.
Usage
swift infer \
--model Qwen/Qwen3-VL-8B-Instruct \
--adapters yzk9/AcciSAGE-S8-SFT
Task-specific prompts and video preprocessing settings are required. This model was developed for research on traffic-accident video understanding.
- Task
- Video-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Created
- Jul 18, 2026
- Updated
- Jul 18, 2026