升级到dtk25.04.2

Dockerfile

-FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.3.0-py3.10-dtk24.04.3-ubuntu20.04
+FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.5.1-ubuntu22.04-dtk25.04.2-py3.10
\ No newline at end of file

Kimi_VL_inference.py

@@ -2,7 +2,7 @@ from PIL import Image
 import torch
 from transformers import AutoModelForCausalLM, AutoProcessor
 
-model_path = "moonshotai/Kimi-VL-A3B-Instruct"
+model_path = "../moonshotai/Kimi-VL-A3B-Instruct"
 model = AutoModelForCausalLM.from_pretrained(
     model_path,
     torch_dtype=torch.bfloat16,
@@ -11,7 +11,7 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
 
-image_path = "/XXX/XXX.jpg"
+image_path = "./xx.png"
 image = Image.open(image_path)
 messages = [
     {"role": "user", "content": [{"type": "image", "image": image_path}, {"type": "text", "text": "Ocr this image."}]}

README.md

@@ -24,7 +24,7 @@ ViT是Google团队提出的将Transformer应用在图像分类的模型。ViT将
 ### Docker（方法一）
 推荐使用docker方式运行， 此处提供[光源](https://www.sourcefind.cn/#/service-details)拉取docker镜像的地址与使用步骤
 ```
-docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.3.0-py3.10-dtk24.04.3-ubuntu20.04
+docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.5.1-ubuntu22.04-dtk25.04.2-py3.10
 
 docker run -it --shm-size=1024G -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal --network=host --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name kimi-vl  <your IMAGE ID> bash # <your IMAGE ID>为以上拉取的docker的镜像ID替换
 
@@ -56,10 +56,10 @@ pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
 
 关于本项目DCU显卡所需的特殊深度学习库可从[光合](https://developer.sourcefind.cn/tool/)开发者社区下载安装。
 ```
-DTK驱动:dtk24.04.3
+DTK驱动:dtk25.04.2
 python:3.10
-torch:2.3.0
-transformers>=4.48.0
+torch:2.5.1
+transformers==4.48.2
 ```
 `Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应`
 

requirements.txt

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