wolf-li

建议配合 github action 使用，不需要单独找 vps 进行部署。

Does the marian model have a method like huggingface generate?

4

Using pipline is slower than using python huggingface library transformers generate function, when the model file is loaded, in using CPU envierment.

Fine-tuning Marian model can't use pipeline doing translate task

2

Fine-tuning Marian model use huggingface transformers library. Translate model to rust_model.ot format. Can't use pipelien translate. This is the erroer message. >Tch tensor error: cannot find the tensor named model.decoder.embed_positions.weight...

nginx 从1.9.0开始，新增加了一个stream模块，用来实现四层协议的转发、代理或者负载均衡等。

作者您好： 想问一下在README.md 中显示测试 mt5 小样本训练结果  您是如何训练的使用？使用的具体是 mt5 那个模型（small、large、base、lx、lxx），可否提供训练具体参数和详细过程？

Hi I try the script use client command: python netcat.py -t 10.10.100.38 -p 5002. No response when using the ctrl +d (EOF). You code is not right. Because it's fine...