Yongliang Shen
Yongliang Shen
你好，感谢关注工作。 在边界识别上，我们为左右边界分别设置了一个识别模块。在左边界和右边界的识别模块上，确实如你问题中直观的理解那样，每一个query对每一个token做询问，得到每个token作为左边界或者右边界的概率，最后选取最大左边界概率对应的token作为实体的左边界，选取最大右边界概率对应的token作为实体的右边界。
@CLNET-pixel Thanks for the suggestion. We will fix this bug ASAP.
Sorry. The Docker files are provided by #34 and have not been rigorously reviewed. We hope that someone could contribute a stable and usable Docker build for Jarvis. Thaks.
Maybe another program is using this port. You can use the `lsof` command to check the status of the port.
Hi @lychees . Can you provide the details of the error? And attach the relevant contents of /server/logs/debug.log
Hi. There is currently a bug that causes an error when setting the httpserver to 0.0.0.0, which we will fix in the next commit.
Hi @canokcan. In `huggingface` mode, Jarvis just calls Hugging Face's online inference endpoint. We check the load status of a particular model via `https://api-inference.huggingface.co/status/dslim/bert-base-NER`. If the remote endpoint is not...
@ForcewithMe66 Hi, you need to set `HUGGINGGPT_BASE_URL` correctly according to the configuration of the server side. For example set `LAN_IP_of_the_server` to your local ip address (If your web and server...
Thanks for your suggestion. We will upload the predictions files within two weeks.
@DhavalRepo18 Sorry for the delay. I have uploaded the prediction files. You can access them at the following link: [Link](https://pan.baidu.com/s/1NryL4DMiO4BQW1blLLWLpw?pwd=8888) Password: 8888