F16 commited on
Commit
8a25f14
1 Parent(s): 0ed885d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +38 -3
README.md CHANGED
@@ -1,3 +1,38 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## How to Get Started with the Model
2
+
3
+ Use the code below to get started with the model.
4
+
5
+ ```python
6
+ import requests
7
+
8
+ from PIL import Image
9
+ from transformers import AutoProcessor, AutoModelForCausalLM
10
+
11
+
12
+ model = AutoModelForCausalLM.from_pretrained("F16/florence2-large-ft-gufeng_v3", trust_remote_code=True)
13
+ processor = AutoProcessor.from_pretrained("F16/florence2-large-ft-gufeng_v3", trust_remote_code=True)
14
+
15
+ prompt = "<MORE_DETAILED_CAPTION>"
16
+
17
+ url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/car.jpg?download=true"
18
+ image = Image.open(requests.get(url, stream=True).raw)
19
+
20
+ inputs = processor(text=prompt, images=image, return_tensors="pt")
21
+
22
+ generated_ids = model.generate(
23
+ input_ids=inputs["input_ids"],
24
+ pixel_values=inputs["pixel_values"],
25
+ max_new_tokens=1024,
26
+ do_sample=False,
27
+ num_beams=3
28
+ )
29
+ generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
30
+
31
+ parsed_answer = processor.post_process_generation(generated_text, task=prompt, image_size=(image.width, image.height))
32
+
33
+ print(parsed_answer)
34
+
35
+ ```
36
+ ---
37
+ license: mit
38
+ ---