Jie Zheng

ValueError: The model did not return a loss from the inputs

2

I did not have this problem before. But I reinstall transformer today. Then the below error occurs. Do anyone have any ideas? ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │...

Multiple GPU inference

1

I do inference of Llama 70b model using 4 16G V100 GPU. I just use model.generate() to generate content. But I found only one GPU is fully utilized each time....

Does finetuning need to follow the Llama 2 system prompt format?

1

The finetuning Llama 2 example uses the oasst1 dataset with the "### Human: ... ### Assistant: " system prompt format. However, Llama 2 uses the following prompt format: ``` [INST]...

### Has this issue been reported before? - [X] I confirm that there is no existing issue, and I have read the **FAQ** ### Operating Environment - **OS**: - **Zotero...

I would like to ask if it is possible to support customizing columns and integrating with Zotero-GPT to generate summaries, results, or any user-defined topics for papers. It is similar...