Zero-Shot Classification
Transformers
Safetensors
English
qwen3_5
feature-extraction
earth-observation
remote-sensing
satellite-imagery
decision-model
multimodal
vision
calibration
lora
custom_code
Instructions to use mx297/EO-Jev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mx297/EO-Jev with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="mx297/EO-Jev", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("mx297/EO-Jev", trust_remote_code=True) model = AutoModel.from_pretrained("mx297/EO-Jev", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 503 Bytes
4a56d40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 | EO-Jev: Decision Model for Earth Observation
Copyright 2026 Mohamed Atef Abouelhadid, Diaa Addeen Abuhani, Muhammad Akhtar Munir, Fahad Shahbaz Khan, Salman Khan
EO-Jev is d3-flash fine-tuned for Earth observation: LoRA adapters trained on public Earth-observation
training splits, merged into the weights (https://arxiv.org/abs/2611.03371). The runtime code is d3-flash's, unchanged.
Based on:
d3-flash (Decision 3.0)
Copyright 2026 vLLM Semantic Router Team
Built on Qwen/Qwen3.5-9B (Apache-2.0).
|