Upload inference.py with huggingface_hub

inference.py

@@ -1,6 +1,6 @@
 from transformers import AutoTokenizer, AutoProcessor, AutoModelForCausalLM
 from qwen_vl_utils import process_vision_info
-model_path = "/vlm/yinxie/code/megatron_ricevl/checkpoint/date_2025_09_12_85malign_26msft_qwen3_8b_resample_oldparameters_pp2-hf"
+model_path = "lmms-lab/LLaVA-One-Vision-1.5-8B-Instruct"
 
 # default: Load the model on the available device(s)
 model = AutoModelForCausalLM.from_pretrained(
@@ -10,19 +10,13 @@ model = AutoModelForCausalLM.from_pretrained(
 # default processer
 processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
 
-# 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 range of 256-1280, to balance performance and cost.
-# min_pixels = 256*28*28
-# max_pixels = 1280*28*28
-# processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
-
 messages = [
     {
         "role": "user",
         "content": [
             {
                 "type": "image",
-                "image": "/vlm/yinxie/code/sakura.png",
+                "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
             },
             {"type": "text", "text": "Describe this image."},
         ],