MK

训练数据集

3

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment：Linux - 版本号/Version：Paddle：2.6 PaddleOCR： 问题相关组件/Related components： - 运行指令/Command Code：python3 tools/train.py -c configs/kie/vi_layoutxlm/re_vi_layoutxlm_xfund_zh.yml - 完整报错/Complete Error Message： [2022/09/13 17:21:04]...

访问hubsvring中的kie_ser报错

1

H:\ocr\PaddleOCR>python tools/test_hubserving.py --server_url=http://127.0.0.1:8871/predict/kie_ser --image_dir=./train_data/XFUND/zh_train/image/ --visualize=false {'msg': 'not enough values to unpack (expected 3, got 2)', 'results': '', 'status': '101'} [2022/10/12 12:06:33] ppocr INFO: Predict time of ./train_data/XFUND/zh_train/image/0.png: 6.928s Traceback (most...

关于kie模型训练，class_list_xfun.txt中没有other这个关键词是否会影响准确度，在标注的时候没有标注other这个关键字

2

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment： - 版本号/Version：Paddle： PaddleOCR： 问题相关组件/Related components： - 运行指令/Command Code： - 完整报错/Complete Error Message：

完整报错：{ "msg": "(External) CUDA error(2), out of memory. \n [Hint: 'cudaErrorMemoryAllocation'. The API call failed because it was unable to allocate enough memory to perform the requested operation. ] (at...

访问ocr_system本地部署服务报错

1

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment：Linux - 版本号/Version：Paddle： 2.6 PaddleOCR： 问题相关组件/Related components： - 运行指令/Command Code：python tools/test_hubserving.py --server_url=http://127.0.0.1:8868/predict/ocr_system --image_dir=./ppstructure/docs/kie/input/ --visualize=false - 完整报错/Complete Error Message：...

如何使用多个GPU去加载模型？

4

code: torchrun --nproc_per_node 2 example_instructions.py --ckpt_dir CodeLlama-13b-Instruct/ --tokenizer_path CodeLlama-13b-Instruct/tokenizer.model --max_seq_len 2048 --max_batch_size 4 checkpoint = torch.load(ckpt_path, map_location="cpu") --> checkpoint = torch.load(ckpt_path, map_location="cuda") 我将cpu改为cuda后，会报下列错误 torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to...

Add support for zhipuai

7

I tried to convert openai to zhipuai, but the result turned out like this, why? 

[Bug]: Can dbrx not use Vllm?

3

### Your current environment python -m vllm.entrypoints.openai.api_server --model /data1/LLM/model/AI-ModelScope/dbrx-instruct --trust-remote-code ### 🐛 Describe the bug ValueError: Model architectures ['DbrxForCausalLM'] are not supported for now. Supported architectures: ['AquilaModel', 'AquilaForCausalLM', 'BaiChuanForCausalLM', 'BaichuanForCausalLM',...