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

model_id = "Devildarker6789/qwen2vl-chartqa"

processor = AutoProcessor.from_pretrained(model_id, min_pixels=256*28*28, max_pixels=512*28*28)
model = Qwen2VLForConditionalGeneration.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)
model.eval()

image = Image.open("your_chart.png").convert("RGB")
question = "What is the highest value in this chart?"

messages = [{"role": "user", "content": [
    {"type": "image", "image": image},
    {"type": "text",  "text": question}
]}]

text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device)

with torch.no_grad():
    out = model.generate(**inputs, max_new_tokens=64, do_sample=False)

print(processor.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Training Details

Quantization: 8-bit during training
LoRA rank: 16, alpha: 32, dropout: 0.05
Optimizer: AdamW, lr=2e-4, cosine scheduler
Batch size: 1 × 16 grad accumulation = 16 effective
Hardware: T4 GPU (Kaggle)


Then click **Save** — and your HF link is:

https://huggingface.co/Devildarker6789/qwen2vl-chartqa