Yaohai Zhou

应该在human_play.py中把 best_policy = PolicyValueNetNumpy(width, height, policy_param)改为 best_policy = PolicyValueNet(width, height, policy_param) 同时最上面解除 from policy_value_net_pytorch import PolicyValueNet # Pytorch 的注释

还要把human_play.py中的 best_policy = PolicyValueNet(width, height, policy_param) 改为 best_policy = PolicyValueNet(width, height, model_file) 也就是说不需要使用pickle

I think this may be caused by the mismatch of KV cache. I am still trying to find the final reason yet. Before the context shift, many previous embeddings are...

> The same code won't work with a multi-process chatbot, but it will work without multiple processes. Why Hi. Can you share your code here? I am also writing the...

Yes. I have changed my code to ```python async for data in chatbot.ask(prompt=decrypted_contents): message = data["message"][len(prev_text):] ``` But another error raises. ``` async for data in chatbot.ask(prompt=decrypted_contents): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ SyntaxError: 'async...

> > > The same code won't work with a multi-process chatbot, but it will work without multiple processes. Why > > > > > > Hi. Can you share...

好的感谢。我理解您的代码了，想请问一下这种写法是否可以解决多session的场景呢？对于每一个用户来说都是单独的session，互相之间不会影响，而且对于单用户而言对话上下文连贯。 Thanks. I have understood your code. And I am also wondering whether this solution can handle the multi-session scenarios? I mean, for each client the commuication session is independent...

Thank you!

How can we use this repo to develop a multi-session backend API? For example, we have many clients talking with ChatGPT and each client should have his own session. Currently,...

我看起来代码里也没有proxy的调用