Update README.md

README.md

@@ -17,7 +17,41 @@ datasets:
 - **Repository:** [VQASynth](https://github.com/remyxai/VQASynth/tree/main)
 - **Paper:** [SpatialVLM](https://arxiv.org/abs/2401.12168)
 
+# Running SpaceFlorence-2
+```
+import requests
+
+import torch
+from PIL import Image
+from transformers import AutoProcessor, AutoModelForCausalLM 
+
+
+device = "cuda:0" if torch.cuda.is_available() else "cpu"
+torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
+
+model = AutoModelForCausalLM.from_pretrained("remyxai/SpaceFlorence-2", trust_remote_code=True).to(device)
+processor = AutoProcessor.from_pretrained("remyxai/SpaceFlorence-2", trust_remote_code=True)
+
+prompt = "<SpatialVQA> How far between the person and the pallet of boxes?"
 
+url = "https://remyx.ai/assets/spatialvlm/warehouse_rgb.jpg?download=true"
+image = Image.open(requests.get(url, stream=True).raw)
+
+inputs = processor(text=prompt, images=image, return_tensors="pt").to(device, torch_dtype)
+
+generated_ids = model.generate(
+    input_ids=inputs["input_ids"],
+    pixel_values=inputs["pixel_values"],
+    max_new_tokens=1024,
+    num_beams=3,
+    do_sample=False
+)
+generated_text = processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
+
+parsed_answer = processor.post_process_generation(generated_text, task="<SpatialVQA>", image_size=(image.width, image.height))
+
+print(parsed_answer)
+```
 
 ## Citation
 ```