GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
pavi-07
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
pavi-07
Model Tree
Qwen/Qwen2.5-VL-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
SatQuery AI is an Edge-First, Multi-Modal Satellite Question-Answering and Geospatial Intelligence system engineered for Indian Earth Observation (EO) missions (ISRO CARTOSAT, RISAT, Sentinel-1/2, and global benchmarks like SECOND and BEN-GE-8K).
For evaluators and collaborators, the system is organized into a connected 3-Link Triad:
[!IMPORTANT] Edge-First Design vs. Cloud Preview: SatQuery AI is engineered strictly for air-gapped, low-power edge deployment on a 6GB VRAM GPU (NVIDIA RTX 4050 Laptop / NVIDIA Jetson Orin 8GB).
The cloud endpoints (Hugging Face Spaces and Model Hub) serve as interactive verification prototypes and model distribution channels. During real operational deployments in remote or disaster-hit corridors, all models (Qwen2.5-VL INT4 + LoRA adapter + Optical-SAR Dual-CNN) execute locally on consumer edge hardware with zero external API calls and zero cloud telemetry leakage.
This adapter was trained and evaluated specifically on Change Detection Visual Question Answering (CDVQA) pairs from the SECOND benchmark dataset:
| Metric | Zero-Shot Base (Qwen2.5-VL-3B) | SatQuery CDVQA LoRA (Fine-Tuned) | Absolute Delta |
|---|---|---|---|
| Accuracy / Exact Match (EM) | 29.80% | 71.2% (71.20%, 95% CI: [67.20%, 75.20%]) | +41.40% pts |
| Expected Calibration Error (ECE) | — | 0.19 (Routing ECE: 0.1985) | Well-Calibrated |
| F1 Score | 0.384 | 0.782 | +103.6% |
| Adapter Swap Latency |
SatQuery AI's MemoryLifecycleManager implements a time-multiplexed dynamic swap slot ensuring peak memory stays strictly below 6GB:
text
+-------------------------------------------------------------+| Resident Base Memory (Always in VRAM) || - PyTorch CUDA Context & OS Display Headroom : 600 MB || - Optical-SAR Cross-Attention Fusion Model : 180 MB || - Bi-Temporal Change Detection Specialist : 750 MB || - Multi-Label Land Cover Specialist : 310 MB || Subtotal Resident Base : 1,840 MB |+-------------------------------------------------------------+| Dynamic Swap Slot (Time-Multiplexed Lifecycle) || - Qwen2.5-VL-3B (INT4 Quantized + LoRA) : 3,820 MB || Peak Active VRAM (Base + VQA Engine) : 5,660 MB |+-------------------------------------------------------------+| Safety Headroom (Activation tensors & cache) : 484 MB |+-------------------------------------------------------------+python
import torchfrom transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessorfrom peft import PeftModel base_model_id = "Qwen/Qwen2.5-VL-3B-Instruct"lora_model_id = "pavi-07/satquery-cdvqa-lora" # 1. Load 4-bit Quantized Base Modelmodel = Qwen2_5_VLForConditionalGeneration.from_pretrained( base_model_id, torch_dtype=torch.float16, device_map="auto")processor = AutoProcessor.from_pretrained(base_model_id) # 2. Attach Fine-Tuned CDVQA LoRA Adaptermodel = PeftModel.from_pretrained(model, lora_model_id)model.eval() print("SatQuery CDVQA LoRA successfully loaded onto edge hardware!")Qwen/Qwen2.5-VL-3B-Instructq_proj, k_proj, v_proj, o_projlr=2e-4, cosine schedule)bf16)This model is licensed under Apache 2.0.
bibtex
@misc{satquery2026, title={SatQuery AI: Edge-First Multi-Modal Satellite Question-Answering System}, author={Vashishtha, Pavitra}, year={2026}, publisher={Hugging Face}, howpublished={\url{https://huggingface.co/pavi-07/satquery-cdvqa-lora}}}| — |
| 4.81 ms |
| Instant runtime swap |
| Adapter VRAM Footprint | — | 15.2 MB | Fits inside swap slot |