[Question]: 示例代码出错

PaddlePaddle / PaddleNLP

👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis etc.

https://paddlenlp.readthedocs.io

Apache License 2.0

12.13k stars 2.94k forks source link

[Question]: 示例代码出错 #8771

Closed yimuu closed 3 months ago

yimuu commented 4 months ago

请提出你的问题

tokenizer = AutoTokenizer.from_pretrained("linly-ai/chinese-llama-2-7b") 这一行代码出错 OSError: Can't load the model for 'linly-ai/chinese-llama-2-7b'. If you were trying to load it from 'BOS', make sure you don't have a local directory with the same name. Otherwise, make sure 'linly-ai/chinese-llama-2-7b' is the correct path to a directory containing one of the ['tokenizer_config.json']

DrownFish19 commented 4 months ago

我们在本地和星河社区执行都是正常的。原因：本地文件默认存储在~/.paddlenlp，可能是由于tokenizer_config.json下载失败导致解决方案：建议删除~/.paddlenlp/models/linly-ai/chinese-llama-2-7b文件夹后再次尝试