Fanbin Mo

表头"sign_in"——数据"sign_in_time" 表头"sign_out"——数据"sign_out_time" 表头"statusText"——数据"status"

[Question]: 训练LORA后模型输出错误

1

### Description 使用与Aquila-chat-lora.yaml的默认配置训练LORA，然后使用generate_chat_lora.py推理，模型输出为乱码： ``` (nndl) root@dl-2306261943226qo-pod-jupyter-7ccbcb95d8-sxjp9:~/FlagAI/examples/Aquila/Aquila-chat# python generate_chat_lora.py ******************** lm aquila-7b ***************use cache True model checkpoint_path=./checkpoints_in/aquila-7b/pytorch_model.bin are loaded successfully... -------------------------------------------------------------------------------- text is Find the product of the numbers: 5 and...

--- name: Pull Request title: 'Fixed an accuracy calculation error in test_eval_gsm.py' assignees: 'BAAI-OpenPlatform,ftgreat' --- ### Description After fine-tuning Aquila using the GSM8K training set, the output may contain "####"....

The label image will be read as NoneType when running this line: `mask = cv2.imread(os.path.join(root+'{}_mask.png').format(id), cv2.IMREAD_GRAYSCALE)` Maybe it should be changed like this: `mask = cv2.imread(os.path.join(root, '{}_mask.png').format(id), cv2.IMREAD_GRAYSCALE)`