-
Failed to run the evaluation script.
-
Hello,
I would like to ask how to create an evaluation dataset.
When I directly run `python evaluate_generation_model.py --model_path ../../LLM_Models/poison-7b-SUDO- --token SUDO --report_path ./…
-
### Required prerequisites
- [X] I have read the documentation .
- [X] I have searched the [Issue Tracker](https://github.com/PKU-Alignment/safe-rlhf/issues) and [Discussions](https://github.com/PKU-…
-
### Required prerequisites
- [X] I have read the documentation .
- [X] I have searched the [Issue Tracker](https://github.com/PKU-Alignment/safe-rlhf/issues) and [Discussions](https://github.com/PKU-…
-
> We preprocess many open-source preference datasets into the standard format and upload them to the hugginface hub. You can find them [HERE](https://huggingface.co/collections/RLHFlow/standard-format…
-
# URL
- https://arxiv.org/abs/2307.04964
# Affiliations
- Rui Zheng, N/A
- Shihan Dou, N/A
- Songyang Gao, N/A
- Wei Shen, N/A
- Binghai Wang, N/A
- Yan Liu, N/A
- Senjie Jin, N/A
- Qi…
-
### SFT data
1. Started the SFT stage with publicly available instruction tuning data ([Chung et al., 2022](https://arxiv.org/pdf/2210.11416))
2. Fewer but high quality > Millions of data but low …
-
Describe the bug
I am trying to finetune tiiuae/falcon-7b-instruct and I am getting this error.
`TypeError: where(): argument 'condition' (position 1) must be Tensor, not bool`
**To Reproduce**…
-
使用deepspeed时候出现
![image](https://github.com/user-attachments/assets/104536ed-3ad5-46b7-8b7f-dab9dc4f5eb0)
参考https://github.com/microsoft/DeepSpeed/issues/1599
https://github.com/PKU-Alignment/safe-…
-
when initializing reward and ref models in step 3 of deepspeed-chat, there are two kinds of deepspeed config files are used, i.e. ds_config and ds_eval_config. May I ask why we need to use two configs…