weather-vlm-qwen2.5-7b

Weather Analysis Vision-Language Model

This model is a fine-tuned version of Qwen2.5-VL-7B for weather and meteorological image analysis.

Model Details

• Base Model: Qwen/Qwen2.5-VL-7B-Instruct
• Fine-tuning Method: LoRA (r=32, alpha=32)
• Checkpoint: checkpoint-7209
• Conversion Date: 2025-07-02T14:34:49.829221

Training Information

{ "global_step": 7209, "epoch": 2.999610014819437, "total_flos": 4.9811140881314e+18, "best_metric": 0.7554888129234314 }

Usage

from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
from PIL import Image
import torch

# Load model and processor
model = Qwen2VLForConditionalGeneration.from_pretrained("qwen2.5VL-7b-weather-sft")
processor = AutoProcessor.from_pretrained("qwen2.5VL-7b-weather-sft")

# Prepare image and prompt
image = Image.open("weather_image.png")
prompt = "Analyze this weather image and describe the meteorological conditions."

# Process inputs
messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": prompt},
            {"type": "image", "image": image},
        ],
    }
]

# Apply chat template
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[image], return_tensors="pt")

# Generate response
with torch.no_grad():
    generated_ids = model.generate(**inputs, max_new_tokens=512)
    generated_ids_trimmed = [
        out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
    ]
    output_text = processor.batch_decode(
        generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
    )[0]

print(output_text)

Specializations

This model has been fine-tuned to excel at:

• Weather pattern recognition
• Meteorological feature identification
• Climate condition analysis
• Atmospheric phenomenon description
• Technical weather terminology

License

Same as base model (Qwen2.5-VL-7B-Instruct)