zhaozg

Kimi_VL_think.py

@@ -2,7 +2,7 @@ from PIL import Image
 import torch
 from transformers import AutoModelForCausalLM, AutoProcessor
 
-model_path = "moonshotai/Kimi-VL-A3B-Thinking"
+model_path = "../moonshotai/Kimi-VL-A3B-Thinking"
 model = AutoModelForCausalLM.from_pretrained(
     model_path,
     torch_dtype=torch.bfloat16,
@@ -20,7 +20,7 @@ model = AutoModelForCausalLM.from_pretrained(
 # )
 processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
 
-image_paths = ["/xxx/Images/1.jpg", "/xxxx/Images/2.jpg"]
+image_paths = ["./Pic/arch.png", "./Pic/theory.png"]
 images = [Image.open(path) for path in image_paths]
 messages = [
     {

requirements.txt

 torch
 torchvision
-transformers>=4.45.0
+transformers==4.48.2
 pillow
 tiktoken
 accelerate