Hongye Liu

监听信息较多导致机器人部分操作无法执行

1

之前的测试号用的一个没加什么群的测试号。代码里面写的关键字回复、拉群全都正常。因为好友上限的限制，换了一个大号。大号加的群较多，控制面板上一直在刷监听到的聊天信息。导致有些关键字没能触发机器人的行为。或者只触发了一半。也没报错。不知道大家有没有遇到这个问题。 等信息较少时发关键字一般能触发。有时候就需要发多次才能触发一次。这种情况也不是机器人掉线了。但是定位不到原因在哪。或者有没有办法不监听群信息，可以控制变量试一下效果。

关于发送小程序的一个疑问。添加好友申请通过自动发送小程序。

3

` if msg.text() == 'test': mini_program_json = {'appid': 'wx7', 'description': '', 'pagePath': None, 'thumbKey': '', 'iconUrl': '', 'thumbUrl': None, 'shareId': '0_wx728d67143_0', 'title': '', 'username': 'gh_dd@app'} loaded_uu_mini_program = self.MiniProgram.create_from_json(payload_data=mini_program_json) await msg.say(loaded_uu_mini_program)...

如题，感谢！

How to fine-tune the pretrain-model

3

I was wondering how to fine-tune the released model in another dataset.

After a few months of learning, I was able to run the example codes and fix some apparent issues. But if I meet some deep issues, I have no idea...

获取token的地方登不上帐号了，请问有人维护吗？

2



Which prompt was used in the paper's result?

4

Thanks for your nice work, I have a short question: I noticed both prompt mechanisms(prefix_prompt and suffix_prompt) were used in all three tasks. So my question is which one is...

Thanks for your code and contribution. I've conducted some testing on the legacy metrics, and it appears there might be an issue with the legacy metric-'best' score. When testing with...

Please make sure you have read the [Wechaty Puppet Service: PadLocal](https://wechaty.js.org/docs/puppet-services/padlocal/) from Wechaty Official Website before you continue writting this issue. ## Question