Boxi Cao
Boxi Cao
Hi, thanks for the repo, it's very interesting work. But I am unable to access the link you provide for checkpoints. It would be so helpful if you could fix...
### 🐛 Describe the bug I failed to install with “CUDA_EXT=1 pip install .” from source, and the error message is: ```bash Installing build dependencies ... done Getting requirements to...
### 🚀 The feature, motivation, and pitch Here is the reply for #365 : > Assume that you having checkpoint output is `best_checkpoint/pytorch_model/mp_rank_00_model_states.pt`. I guess you can try something like...
The repository uses transformers version 4.18, which does not support bloom, is there any way to use bloom as the initial policy for training?
The latest metrics loaded from huggingface such as rouge requires `rouge_score>=0.1.2`， but rl4lms 0.2.1 requires rouge_score==0.0.4, which is incompatible. And will cause errors when running the example in readme file.
Very nice library! I noticed that the current examples are for math task training. Would you consider adding an example for code generation tasks, including some recommended settings? Moreover, while...
### 先决条件 - [x] 我已经搜索过 [问题](https://github.com/open-compass/opencompass/issues/) 和 [讨论](https://github.com/open-compass/opencompass/discussions) 但未得到预期的帮助。 - [x] 错误在 [最新版本](https://github.com/open-compass/opencompass) 中尚未被修复。 ### 问题类型 我正在使用官方支持的任务/模型/数据集进行评估。 ### 环境 ``` {'CUDA available': True, 'CUDA_HOME': '/usr/local/cuda', 'GCC': 'gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0',...
