ottokevin

JUSTCSL-OphthaVision-3B

Deploy Dedicated

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

Metrics (Test Set)

Metric	Value
Accuracy	78.1%
Weighted F1	0.74
Macro F1	0.45
No DR F1	0.955
Moderate F1	0.708
Avg Latency (GPU)	1.16s

Usage

python
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
import torch

model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    "ottokevin/JUSTCSL-OphthaVision-3B",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
processor = AutoProcessor.from_pretrained("ottokevin/JUSTCSL-OphthaVision-3B")

# Prepare image + prompt
from PIL import Image
image = Image.open("retina.png").convert("RGB")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "image": image},
            {"type": "text", "text": "Classify this retina image: 0=No DR, 1=Mild, 2=Moderate, 3=Severe, 4=Proliferative DR. Answer:"},
        ],
    },
]
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[image], padding=True, return_tensors="pt").to(model.device)
generated = model.generate(**inputs, max_new_tokens=8, do_sample=False)
response = processor.tokenizer.decode(generated[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(response)