Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,100 @@
+---
+base_model: LiquidAI/LFM2.5-VL-450M
+tags:
+- vision-language
+- satellite
+- vrsbench
+- lfm2
+- gguf
+- remote-sensing
+---
+
+# LFM2.5-VL-450M VRSBench LoRA
+
+## Model Description
+
+This is a fine-tuned version of LiquidAI's LFM2.5-VL-450M vision-language model, trained on the VRSBench dataset for general satellite image understanding. This serves as the base model for specialized satellite vision tasks.
+
+The model can answer questions about satellite imagery, including:
+- Scene classification
+- Object detection and counting
+- Visual question answering about satellite images
+- General satellite image understanding
+
+## Training Details
+
+### VRSBench Training
+- **Base Model**: LFM2.5-VL-450M
+- **Dataset**: VRSBench (Vision Reasoning and Scene Understanding Benchmark)
+- **Epochs**: 1
+- **Method**: LoRA (r=16, alpha=32)
+- **Hardware**: Local GPU training (no Ray/distributed)
+
+## Derived Models
+
+This model serves as the base for specialized satellite vision experts:
+
+| Model | Dataset | Task | Accuracy/Performance |
+|-------|----------|------|---------------------|
+| [VRSBench + EuroSAT Terrain Expert](https://huggingface.co/5ch4um1/lfm2.5-vrsbench-EUROSAT-terrain-lora-450m) | EuroSAT | Terrain Classification | 97.52% accuracy |
+| [VRSBench + MADOS Maritime Expert](https://huggingface.co/5ch4um1/lfm2.5-vrsbench-mados-maritime-lora-450m) | MADOS | Maritime Detection | IoU@0.5: ~2% |
+
+## Usage
+
+### With llama.cpp
+
+```bash
+# Download Q4_K_M quantized version (recommended)
+wget https://huggingface.co/5ch4um1/lfm2.5-vrsbench-lora-450m/resolve/main/lfm2.5-vrsbench-lora-450m-q4_k_m.gguf
+
+# Run inference
+./llama-cli -m lfm2.5-vrsbench-lora-450m-q4_k_m.gguf \
+  --image satellite_image.jpg \
+  -p "Describe this satellite image in detail."
+```
+
+### With Transformers
+
+```python
+from transformers import AutoModelForVision2Seq, AutoProcessor
+from PIL import Image
+
+model = AutoModelForVision2Seq.from_pretrained(
+    "5ch4um1/lfm2.5-vrsbench-lora-450m",
+    torch_dtype="auto",
+    device_map="auto"
+)
+processor = AutoProcessor.from_pretrained("5ch4um1/lfm2.5-vrsbench-lora-450m")
+
+image = Image.open("satellite_image.jpg")
+prompt = "What is shown in this satellite image?"
+
+inputs = processor(text=prompt, images=image, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=100)
+print(processor.decode(outputs[0], skip_special_tokens=True))
+```
+
+## GGUF Quantizations
+
+| Version | Size | Description |
+|---------|------|-------------|
+| F16 | 679 MB | Full precision (16-bit) |
+| Q8_0 | 362 MB | 8-bit quantization |
+| Q4_K_M | 219 MB | 4-bit quantization (recommended for most use cases) |
+
+## Model Sources
+
+- **Base Model**: [LiquidAI/LFM2.5-VL-450M](https://huggingface.co/LiquidAI/LFM2.5-VL-450M)
+- **VRSBench Dataset**: [VRSBench Paper](https://arxiv.org/abs/)
+
+## Limitations
+
+- General satellite understanding model - not specialized for specific tasks
+- Performance varies depending on satellite image type and task
+- For specialized tasks (terrain, maritime), use the derived expert models listed above
+
+## Training Environment
+
+- **Framework**: Transformers + PEFT (LoRA)
+- **Hardware**: Local GPU (CUDA)
+- **Training Scripts**: Available in the [cookbook repository](https://github.com/anomalyco/opencode)