下一块巧克力

Results 3 issues of 下一块巧克力

### Reminder - [X] I have read the README and searched the existing issues. ### System Info 为了解决exposure bias问题,即train阶段是teaching force,而infer阶段是仅依赖自己生成的pre token,这种情况会加剧幻觉。典型的解决方案就是在训练阶段引入scheduled sampling。 ### Reproduction none ### Expected behavior _No response_...

pending

### 🚀 The feature, motivation and pitch Basically in decoding stage, we use sampling strategy with parameters like top_p/top_k/temp/xx_penalty to control the diversity of the generated content. However beam_search is...

feature request

### Required prerequisites - [x] I have searched the [Issue Tracker](https://github.com/camel-ai/camel/issues) and [Discussions](https://github.com/camel-ai/camel/discussions) that this hasn't already been reported. (+1 or comment there if it has.) - [x] Consider asking...

enhancement
New Feature
call for contribution