GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Brusnicki
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Brusnicki
Model Tree
Qwen/Qwen2.5-VL-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
LoRA adapter for Qwen/Qwen2.5-VL-7B-Instruct, fine-tuned for binary anomaly detection in autonomous driving scenes. Given a front-camera image, the model classifies the scene as anomaly or normal.
This is the direct classification model of the SAVANT framework — a single-shot approach that achieves the best accuracy among the evaluated configurations.
Evaluated on a balanced test set of 1,020 driving scene images:
| Metric | Value |
|---|---|
| Accuracy | 93.8% |
| Precision | 96.7% |
| Recall | 90.8% |
| F1-Score | 93.6% |
| Parameter | Value |
|---|---|
| Rank (r) | 16 |
| Alpha | 32 |
| Dropout | 0.05 |
| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj, fc1, fc2, qkv, mlp.0, mlp.2 |
python
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom peft import PeftModelimport torch # Load base modelbase_model = Qwen2_5_VLForConditionalGeneration.from_pretrained( "Qwen/Qwen2.5-VL-7B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") # Load LoRA adaptermodel = PeftModel.from_pretrained(base_model, "u94fmn391j/SAVANT-anomaly-classifier-lora") # Load processorprocessor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")bibtex
@article{brusnicki2025can, title={Can VLMs Unlock Semantic Anomaly Detection? A Framework for Structured Reasoning}, author={Brusnicki, Roberto and Pop, David and Gao, Yuan and Piccinini, Mattia and Betz, Johannes}, journal={arXiv preprint arXiv:2510.18034}, year={2025}}from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom peft import PeftModelimport torch # Load base modelbase_model = Qwen2_5_VLForConditionalGeneration.from_pretrained( "Qwen/Qwen2.5-VL-7B-Instruct", torch_dtype=torch.bfloat16, device_map="auto") # Load LoRA adaptermodel = PeftModel.from_pretrained(base_model, "u94fmn391j/SAVANT-anomaly-classifier-lora") # Load processorprocessor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")@article{brusnicki2025can, title={Can VLMs Unlock Semantic Anomaly Detection? A Framework for Structured Reasoning}, author={Brusnicki, Roberto and Pop, David and Gao, Yuan and Piccinini, Mattia and Betz, Johannes}, journal={arXiv preprint arXiv:2510.18034}, year={2025}}