-
你好，我目前先在deepke上用自己的数据集进行微调，环境是windows系统。以下是我的脚本
output_dir='lora/oneke-continue'
mkdir -p ${output_dir}
CUDA_VISIBLE_DEVICES="0" torchrun --nproc_per_node=1 --master_port=1287 src/finetune.py \
…
-
您好，我在按照readme的步骤操作，在运行DeepKE\example\re\standard\run.py时出现错误：
'HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /bert-base-chinese/resolve/main/vocab.txt (Caused b…
-
### Bug Description
我利用本地的embedding模型进行加载，定义为
vector_store = Neo4jVectorStore(username, password, url, embed_dim=1024)
service_context = ServiceContext.from_defaults(
llm_predictor=llm_predict…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
我使用自己的向量模型“bge-large-zh”
vector_store = Neo4jVectorStore(username, password, url, 1024)…
-
**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 Versi…
-
完全参考例子：
https://github.com/zjunlp/DeepKE/blob/main/example/llm/OneKE.md#%E5%BF%AB%E9%80%9F%E8%BF%90%E8%A1%8C
system_prompt = '\nYou are a helpful assistant. 你是一个乐于助人的助手。\n\n\n'
sintruct = "{\"ins…
-
**Describe the bug**
> A clear and concise description of what the bug is.
使用官方给的脚本https://github.com/zjunlp/DeepKE/blob/main/example/llm/OneKE.md，运行后报错
Traceback (most recent call last):
File…
-
**Describe the question**
> A clear and concise description of what the question is.
请问对模型进行二次训练，对数据集格式有什么具体要求吗？我看文档中提到可以用doccano标注数据，可以之间使用不需要预处理吗？
**Environment (please complete the followi…
-
**Describe the bug**
> A clear and concise description of what the bug is.
Taken the following installation steps:
created clean conda environment (python=3.8)
pip install -r requirements.txt
…
-
您好，deepke-llm是否支持baichuan2-13b-chat-4bits直接进行合并权重预测