simon gao

请将项目名发送到[email protected]，我删除镜像重建一下再试，另外，gitclone.com不支持递归clone

use key property,when key was changed then render immediately,such as: ``

added pad_token_id = 50256 such as : ``` pad_token_id = 50256 set_seed(42, deterministic=True) device = torch.device('cuda:0') ... ... ```

@pansinm 感谢pansinm，已按您的方法解决。 1、为了避免以下错误：ValueError: Loading ./model/ requires you to execute the tokenizer file in that repo on your local machine. Make sure you have read the code there to avoid malicious...

AutoTokenizer.from_pretrained(模型名)是从缓存加载模型的，问题是transformers首先要从huggingface取commit_hash比对本地的缓存是不是最新的，这一步过不去，还没到从本地cache装模型那一步。

The flash_attn is not supported.Use load_in_8bit,peft technology and bitsandbytes to accelerate.It requires about 13G of GPU memory. [https://github.com/git-cloner/llama-lora-fine-tuning#341-fine-tuning-command](https://github.com/git-cloner/llama-lora-fine-tuning#341-fine-tuning-command) for the training script train_lora.py needs to be modified, refer to: [https://github.com/git-cloner/llama-lora-fine-tuning/blob/main/fastchat/train/train_lora.py...

@zl1994 Multi gpu will encounter RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu, which has not been resolved yet.

If you have multiple GPUs, update fastchat/train/train_lora.py and using --num_gpus parameter,such as : CUDA_VISIBLE_DEVICES=0,1 \ deepspeed --num_gpus=2 fastchat/train/train_lora.py \ --deepspeed ./deepspeed-config.json \ --lora_r 8 \ ... ... https://github.com/git-cloner/llama-lora-fine-tuning/blob/main/fastchat/train/train_lora.py and https://github.com/git-cloner/llama-lora-fine-tuning#341-fine-tuning-command

Not LoRa reason, it's because of flash_attn problem, you need to test on the 3090 to see if flash_attn is getting an error

you can wrap this model into a web application, provide code generation services, and develop a vs code extension that generates code snippets when pressed ':' or '{'. such as...