Instructions to use RetrO21/AgriModelLo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RetrO21/AgriModelLo with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "RetrO21/AgriModelLo")

Transformers

How to use RetrO21/AgriModelLo with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="RetrO21/AgriModelLo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("RetrO21/AgriModelLo", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RetrO21/AgriModelLo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RetrO21/AgriModelLo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RetrO21/AgriModelLo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RetrO21/AgriModelLo

SGLang

How to use RetrO21/AgriModelLo with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "RetrO21/AgriModelLo" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RetrO21/AgriModelLo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "RetrO21/AgriModelLo" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RetrO21/AgriModelLo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RetrO21/AgriModelLo with Docker Model Runner:
```
docker model run hf.co/RetrO21/AgriModelLo
```

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)

Downloads last month: 2

Model tree for RetrO21/AgriModelLo

Base model

Qwen/Qwen2-VL-7B

Finetuned

Qwen/Qwen2-VL-7B-Instruct

Adapter

(211)

this model