GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Brusnicki
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
Brusnicki
Model Tree
Base
Qwen/Qwen2.5-VL-7B-Instruct
Adapter
this model
Input Modalities
Text
Image
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
LoRA adapter for Qwen/Qwen2.5-VL-7B-Instruct, fine-tuned for anomaly evaluation using both the driving scene image and a structured scene description. This is Phase 2 of the SAVANT two-phase pipeline.
The model receives:
And outputs a binary anomaly classification with detailed reasoning.
When used as part of the full SAVANT pipeline (Phase 1 + Phase 2), evaluated on a balanced test set of 1,020 driving scene images:
| Metric | Value |
|---|---|
| Accuracy | 83.7% |
| Precision | 85.1% |
| Recall | 81.8% |
| F1-Score | 83.4% |
| 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 torchbase_model = Qwen2_5_VLForConditionalGeneration.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct",torch_dtype=torch.bfloat16,device_map="auto")model = PeftModel.from_pretrained(base_model, "u94fmn391j/SAVANT-multimodal-evaluation-lora")processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")