DeepKE
DeepKE copied to clipboard
zjunlp
[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction
**Describe the bug** > A clear and concise description of what the bug is. using pip install deepke get error from console: ERROR: pip's dependency resolver does not currently take...
**Describe the question** > A clear and concise description of what the question is. File "C:\Users\DuYH\AppData\Local\Programs\Python\Python38\lib\site-packages\transformers\tokenization_utils_base.py", line 1584, in from_pretrained raise EnvironmentError( OSError: Model name 'bert-base-chinese' was not found in...
运行结果 不理想
运行 example/triple下的例子， text为 河南村镇银行400亿金融犯罪背后：第三方支付平台“功不可没” 背后是周鸿祎雷军还有中国人寿：苦主颗粒无归 输出为： ``` [2022-07-29 11:45:49,666][__main__][INFO] - [(' ', '[SEP]'), ('周', 'B-YAS'), ('鸿', 'I-YAS'), ('祎', 'I-YAS'), ('雷', 'B-YAS'), ('军', 'I-YAS'), ('中', 'B-CAR'), ('国', 'I-CAR')] [2022-07-29 11:45:49,666][__main__][INFO] -...
## Describe the feature 在Docker上部署的时候遇到了很多文档与issues中没有的问题，所以我决定试着使用Docker部署以一下，然后把遇到的问题与 解决方案分享出来，给大家参考一下 ## Environment : - OS: win10.docker v20.10.17 - Python Version 3.8 ## 从“Quick Start”开始 ### 下载并构建镜像 `git clone`之后进入docker文件夹，（或许这里可以直接单独下载DeepKE/docker/DockerFile文件） 过程中可能`error: RPC failed; curl 56 GnuTLS...
**Describe the question** > A clear and concise description of what the question is. **Environment (please complete the following information):** - OS: [e.g. mac / window] - Python Version [e.g....
使用案例：DeepKE训练关系抽取时候，如果输入文本长度超过512就会报错。这个希望加一个后处理功能，超过512的，进行分段抽取再汇总返回结果。而不是报错。 
**Describe the bug** > A clear and concise description of what the bug is. 运行那个样本代码 >>> model = AutoModelForCausalLM.from_pretrained( ... model_path, ... config=config, ... device_map="auto", ... quantization_config=quantization_config, ... torch_dtype=torch.bfloat16, ......
**Describe the feature** > A clear and concise description of any features you've considered. **Environment (please complete the following information):** - OS: [e.g. mac / window] - Python Version [e.g....
在案例：Lora微调Baichuan完成CCKS2023指令驱动的知识图谱构建 中，我尝试使用训练好的baichuan2-13b-iepile-lora模型进行预测，这是我的bash文件：`CUDA_VISIBLE_DEVICES=0 python src/inference.py \ --stage sft \ --model_name_or_path 'zjunlp/baichuan2-13b-iepile-lora' \ --checkpoint_dir 'lora/baichuan2-13b-iepile-lora' \ --model_name 'baichuan' \ --template 'baichuan2' \ --do_predict \ --input_file 'data/input.json' \ --output_file 'results/baichuan2-13b-iepile-lora_output.json' \ --finetuning_type lora...
**Describe the bug** > A clear and concise description of what the bug is. 【问题】 调用OneKE模型库，输出内容不可解析的JSON，内容大量重复。 **Environment (please complete the following information):** - OS: [e.g. mac / window] - Python...
