Update README.md

README.md

@@ -52,24 +52,7 @@ PIXAR-7B achieves **2.6× IoU improvement** over prior state of the art on the P
 
 ## How to Get Started
 
-```python
-from transformers import AutoTokenizer
-from model.PIXAR import PIXARForCausalLM
-
-model = PIXARForCausalLM.from_pretrained(
-    "jiachengcui888/PIXAR-7B",
-    low_cpu_mem_usage=True,
-    vision_tower="openai/clip-vit-large-patch14",
-    seg_token_idx=seg_token_idx,
-    cls_token_idx=cls_token_idx,
-    obj_token_idx=obj_token_idx,
-    num_obj_classes=81,
-    seg_prompt_mode="seg_only",
-    torch_dtype=torch.bfloat16,
-).cuda()
-```
-
-For interactive inference, see the [project repository](https://github.com/Jiacheng8/PIXAR):
+For interactive inference, see the [project repository](https://github.com/VILA-Lab/PIXAR):
 
 ```bash
 python chat.py --version jiachengcui888/PIXAR-7B --precision bf16 --seg_prompt_mode seg_only