xlnn

### Question Thank you for your excellent work. May I ask if there is a 7B-sized file of Llama_2_7b_chat_freeze?

### Description 将pot翻译集插件成到到zotero7中 ### Application Scenario 阅读文献 ### References _No response_

CUDA Out of Memory Error on a 32GB GPU when Running trainer.py for Fine-Tuning

8

**Description**: Hello, I encountered a `torch.cuda.OutOfMemoryError` while fine-tuning a model using `trainer.py`. My setup includes only a single GPU with 32GB of memory, and the error occurs even at the...

Could you please explain how to run this experiment using multiple GPUs?

1

Thank you for the excellent work. Could you please explain how to run this experiment using multiple GPUs?

I hope this message finds you well. I am currently working on a research project related to adversarial examples and large language models, and I came across your excellent paper...

Thank you for your excellent work. May I ask if there is a 7B-sized file of Llama_2_7b_chat_freeze?

The results are all target_loss: 10.375000.Why?

2

``` Hello~Congratulations on the great work! The configuration is as follows（https://huggingface.co/lmsys/vicuna-7b-delta-v0）： # Vicuna llama_model: "/home/Visual/vicuna-7b-delta-v0-weights" ``` >>> batch_size: 8 0%| | 0/5001 [00:00

How can i debug these codes?