metadata
base_model: Qwen/Qwen2-VL-7B-Instruct
library_name: peft
model_name: AgriAssist
tags:
- vision-language
- agriculture
- crop-detection
- pest-detection
- weed-detection
- fine-tuning
- sft
- lora
- transformers
license: apache-2.0
pipeline_tag: text-generation
AgriAssist: Domain-Specific Vision-Language Model for Indian Agriculture
AgriAssist is a fine-tuned vision-language model (VLM) built on Qwen2-VL-7B-Instruct, designed specifically for Indian agricultural applications. It is trained on curated datasets covering major crops, weeds, pests, and diseases, enabling robust recognition and basic reasoning over agricultural images.
Features
- Domain-specific fine-tuning for Indian agriculture
- Recognition of crops, weeds, and pests
- Instruction-tuned for multimodal reasoning
- Trained on multiple public datasets: MH-Weed16, PlantVillage, AgroBench
- Ready for integration in applications requiring agricultural image understanding
Usage
from transformers import AutoProcessor, AutoModelForCausalLM
processor = AutoProcessor.from_pretrained("your-username/AgriAssist")
model = AutoModelForCausalLM.from_pretrained("your-username/AgriAssist")
# Example usage
inputs = processor(images=image_list, text="Identify the pest in the image", return_tensors="pt")
outputs = model.generate(**inputs)