llama-lora-fine-tuning
llama-lora-fine-tuning copied to clipboard
git-cloner
llama fine-tuning with lora
May I ask the result of this lora fine-tuning on MMLU task. Thanks! Best, Lucas
my commonda to test the finetuned model ! CUDA_VISIBLE_DEVICES=0 python generate.py --base_model '/content/drive/MyDrive/Colab Notebooks/llama_finetuning/llama-lora-fine-tuning/llama-7b-hf' --lora_weights '/content/drive/MyDrive/Colab Notebooks/llama_finetuning/output' error CUDA SETUP: Loading binary /usr/local/lib/python3.10/dist-packages/bitsandbytes/libbitsandbytes_cuda118.so... [2023-08-18 02:27:44,650] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to...
I get this error when I run `deepspeed fastchat/train/train_lora.py` ValueError: Asking to pad but the tokenizer does not have a padding token. Please select a token to use as `pad_token`...
When I try to resume training from a checkpoint, it says ValueError: Expected a cuda device, but got: cpu. How do I fix this?
Two 3060 graphics cards with a total memory of 24GB, why would this error still be reported? 
Token indices sequence length is longer than the specified maximum sequence length for this model (2189 > 2048). Running this sequence through the model will result in indexing errors
Very good project, I wonder if you can provide the code for merging the generated output file into the original model?
As the picture below,It didn't start training for a long time.Is it reasonable or the reason of V100 8-bit matmul is slow? Thanks for your help.
pip3 install -r requirements.txt -i https://pypi.mirrors.ustc.edu.cn/simple --trusted-host=pypi.mirrors.ustc.edu.cn: