22zhangqian

我也是在微调代码的时候，运行train.sh文件遇到RuntimeError: Internal: src/sentencepiece_processor.cc(1101) [model_proto->ParseFromArray(serialized.data(), serialized.size())]这个错误，请问是怎么回事？

我得到了解决方案，只要从baichuan源模型文件里复制configuration_baichuan.py等文件放到我们合并的路径中就可以正常跑通了 应该是合并的代码没有保存那几个文件

me too, there always appear some "### Instruction:". and need a long time to generate answer, and, if i ask it "tell me about alpaca", it will give me answer,...

torchrun --nproc_per_node=8 --master_port=29005 finetune.py \ --base_model='/remote-home/alpaca-llama-lora-7B-13B-65B/llama-13b-hf' \ --data_path 'data/data-10w.json' \ --output_dir='output/lora-alpaca-13' \ --batch_size 128 \ --micro_batch_size 2 \ --num_epochs 2 I have encountered the same problem. Can you help me？

确实，请问可以提供一个requirements.txt吗？不然部署起来着实有点麻烦