Instructions to use uer/roberta-base-chinese-extractive-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use uer/roberta-base-chinese-extractive-qa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="uer/roberta-base-chinese-extractive-qa")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("uer/roberta-base-chinese-extractive-qa") model = AutoModelForQuestionAnswering.from_pretrained("uer/roberta-base-chinese-extractive-qa") - Inference
- Notebooks
- Google Colab
- Kaggle
本地输出总是为全context,但是网页demo输出正确,是否缺少预测步骤?
#2
by yinghy18 - opened
我重新安装了python3.8(原来是3.7)并重新安装了依赖,就对了
Package Version
certifi 2024.2.2
charset-normalizer 3.3.2
colorama 0.4.6
filelock 3.13.3
fsspec 2024.3.1
huggingface-hub 0.22.1
idna 3.6
numpy 1.24.4
packaging 24.0
pip 20.2.3
PyYAML 6.0.1
regex 2023.12.25
requests 2.31.0
safetensors 0.4.2
setuptools 49.2.1
tokenizers 0.15.2
torch 1.8.0
tqdm 4.66.2
transformers 4.39.1
typing-extensions 4.10.0
urllib3 2.2.1

