升级至dtk25.04.2

Dockerfile

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

README.md

@@ -25,7 +25,7 @@
 ### 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 minicpm_v  <your IMAGE ID> bash # <your IMAGE ID>为以上拉取的docker的镜像ID替换
 
 git clone http://developer.sourcefind.cn/codes/modelzoo/minicpm-v-2_6_pytorch.git
@@ -55,9 +55,9 @@ 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
+torch:2.5.1
 transformers==4.48.3
 ```
 `Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应`

finetune.sh

-CUDA_VISIBLE_DEVICES=0,1,2,3 \
+CUDA_VISIBLE_DEVICES=4,5,6,7 \
 swift sft \
-    --model "OpenBMB/MiniCPM-V-2_6" \
+    --model "../OpenBMB/MiniCPM-V-2_6" \
     --dataset AI-ModelScope/LaTeX_OCR:human_handwrite#20000 \
     --train_type lora \
     --torch_dtype bfloat16 \

minicpm-v_version.py

@@ -3,12 +3,12 @@ import torch
 from PIL import Image
 from modelscope import AutoModel, AutoTokenizer
 
-model = AutoModel.from_pretrained('OpenBMB/MiniCPM-V-2_6', trust_remote_code=True,
+model = AutoModel.from_pretrained('../OpenBMB/MiniCPM-V-2_6', trust_remote_code=True,
     attn_implementation='sdpa', torch_dtype=torch.bfloat16) # sdpa or flash_attention_2, no eager
 model = model.eval().cuda()
-tokenizer = AutoTokenizer.from_pretrained('OpenBMB/MiniCPM-V-2_6', trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained('../OpenBMB/MiniCPM-V-2_6', trust_remote_code=True)
 
-image = Image.open('xx.jpg').convert('RGB')
+image = Image.open('./icon.png').convert('RGB')
 question = 'What is in the image?'
 msgs = [{'role': 'user', 'content': [image, question]}]
 

requirements.txt

@@ -11,3 +11,4 @@ decord
 moviepy==1.0.3
 modelscope
 numpy==1.26.0
+soxr