Update README.md

README.md

@@ -73,24 +73,24 @@ from qwen_vl_utils import process_vision_info
 
 # default: Load the model on the available device(s)
 model = AutoModelForImageTextToText.from_pretrained(
-    "phronetic-ai/Qwen2-VL-DAPO", torch_dtype="auto", device_map="auto"
+    "phronetic-ai/RZN-V", torch_dtype="auto", device_map="auto"
 )
 
 # We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
 # model = AutoModelForImageTextToText.from_pretrained(
-#     "phronetic-ai/Qwen2-VL-DAPO",
+#     "phronetic-ai/RZN-V",
 #     torch_dtype=torch.bfloat16,
 #     attn_implementation="flash_attention_2",
 #     device_map="auto",
 # )
 
 # default processer
-processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
+processor = AutoProcessor.from_pretrained("phronetic-ai/RZN-V")
 
 # The default range for the number of visual tokens per image in the model is 4-16384. You can set min_pixels and max_pixels according to your needs, such as a token count range of 256-1280, to balance speed and memory usage.
 # min_pixels = 256*28*28
 # max_pixels = 1280*28*28
-# processor = AutoProcessor.from_pretrained("phronetic-ai/Qwen2-VL-DAPO", min_pixels=min_pixels, max_pixels=max_pixels)
+# processor = AutoProcessor.from_pretrained("phronetic-ai/RZN-V", min_pixels=min_pixels, max_pixels=max_pixels)
 
 messages = [
     {