Views
No views yet
| Release | VQAv2 | GQA | TextVQA | TallyQA (simple) | TallyQA (full) |
|---|---|---|---|---|---|
| 2024-03-04 | 74.2 | 58.5 | 36.4 | - | - |
| 2024-03-06 | 75.4 | 59.8 | 43.1 | 79.5 | 73.2 |
| 2024-03-13 | 76.8 | 60.6 | 46.4 | 79.6 | 73.3 |
| 2024-04-02 | 77.7 | 61.7 | 49.7 | 80.1 | 74.2 |
| 2024-05-08 | 79.0 | 62.7 | 53.1 | 81.6 | 76.1 |
| 2024-05-20 (latest) | 79.4 | 63.1 | 57.2 | 82.1 | 76.6 |
pip install transformers einops1from transformers import AutoModelForCausalLM, AutoTokenizer
2from PIL import Image
3
4model_id = "vikhyatk/moondream2"
5revision = "2024-05-20"
6model = AutoModelForCausalLM.from_pretrained(
7 model_id, trust_remote_code=True, revision=revision
8)
9tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)
10
11image = Image.open('<IMAGE_PATH>')
12enc_image = model.encode_image(image)
13print(model.answer_question(enc_image, "Describe this image.", tokenizer))