Base Model :

  • vikhyatk/moondream2

Dataset :

  • project-sloth/captcha-images

Load model :


from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image

model_id = "ayoubkirouane/moondream2-image-captcha"
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained(model_id , trust_remote_code=True)

image = Image.open('/content/test.png')
enc_image = model.encode_image(image)
print(model.answer_question(enc_image, "What does the text say?", tokenizer))

Downloads last month
44
Safetensors
Model size
1.87B params
Tensor type
FP16
·
Inference API
Inference API (serverless) does not yet support model repos that contain custom code.

Datasets used to train ayoubkirouane/moondream2-image-captcha