gokaygokay commited on
Commit
6525661
1 Parent(s): 452ccc6

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +36 -0
README.md CHANGED
@@ -1,3 +1,39 @@
1
  ---
2
  license: apache-2.0
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ pipeline_tag: image-text-to-text
4
  ---
5
+
6
+ moondream2 is a small vision language model designed to run efficiently on edge devices. Check out the [GitHub repository](https://github.com/vikhyat/moondream) for details, or try it out on the [Hugging Face Space](https://huggingface.co/spaces/vikhyatk/moondream2)!
7
+
8
+ **Benchmarks**
9
+
10
+ | Release | VQAv2 | GQA | TextVQA | TallyQA (simple) | TallyQA (full) |
11
+ | --- | --- | --- | --- | --- | --- |
12
+ | 2024-03-04 | 74.2 | 58.5 | 36.4 | - | - |
13
+ | 2024-03-06 | 75.4 | 59.8 | 43.1 | 79.5 | 73.2 |
14
+ | **2024-03-13** (latest) | 76.8 | 60.6 | 46.4 | 79.6 | 73.3 |
15
+
16
+ **Usage**
17
+
18
+ ```bash
19
+ pip install transformers timm einops
20
+ ```
21
+
22
+ ```python
23
+ from transformers import AutoModelForCausalLM, AutoTokenizer
24
+ from PIL import Image
25
+
26
+ model_id = "vikhyatk/moondream2"
27
+ revision = "2024-03-06"
28
+ model = AutoModelForCausalLM.from_pretrained(
29
+ model_id, trust_remote_code=True, revision=revision
30
+ )
31
+ tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)
32
+
33
+ image = Image.open('<IMAGE_PATH>')
34
+ enc_image = model.encode_image(image)
35
+ print(model.answer_question(enc_image, "Describe this image.", tokenizer))
36
+ ```
37
+
38
+ The model is updated regularly, so we recommend pinning the model version to a
39
+ specific release as shown above.