Update README.md

README.md

@@ -6,4 +6,37 @@ base_model:
 ---
 
 
-A finetuned version of MiniCPM-V 2.6 on GQA-it: Italian Question Answering on Image Scene Graph
+<h1>A finetuned version of MiniCPM-V 2.6 on GQA-it: Italian Question Answering on Image Scene Graph</h1>
+
+
+# Usage
+Checkout the github repository for more insights and codes: https://github.com/crux82/XXXXXX
+
+```python
+import torch
+from PIL import Image
+from transformers import AutoModel, AutoTokenizer,AutoProcessor
+
+model = AutoModel.from_pretrained('sag-uniroma2/MiniCPM-V-2_6-gqa-it-finetuned', trust_remote_code=True,
+                                  attn_implementation='sdpa', torch_dtype=torch.bfloat16)
+model = model.eval().cuda()
+tokenizer = AutoTokenizer.from_pretrained('openbmb/MiniCPM-V-2_6', trust_remote_code=True)
+img="xx.jpg"
+image = Image.open(img).convert('RGB')
+
+question = "C'è un idrante sull'erba?"
+msgs = [{'role': 'user', 'content': [image,question]}]
+
+answer = model.chat(
+    image=None,
+    msgs=msgs,
+    tokenizer=tokenizer
+)
+print(answer)
+
+```
+
+# Citation
+```
+TODO
+```