InstructGLM icon indicating copy to clipboard operation
InstructGLM copied to clipboard

ChatGLM-6B 指令学习|指令数据|Instruct

Results 22 InstructGLM issues
Sort by recently updated
recently updated
newest added

When running 'train_deepspeed.py' using your provided command, I noticed that the trainable parameter number is consistently zero. So, I performed a thorough code analysis and pinpointed the root cause of...

训练的时候提示如下错误: ``` (venv) [xinjingjing@dev-gpu-node-09 InstructGLM]$ python train_lora.py \ > --dataset_path data/belle \ > --lora_rank 8 \ > --per_device_train_batch_size 2 \ > --gradient_accumulation_steps 1 \ > --max_steps 52000 \ > --save_steps...

太糟糕的话,感觉就有点不太行了。

按照前序预处理成json格式后,运行tokenizer_dataset_row.py报错: dataset=datasets.Dataset.from_generator(..) ... file"/usr/local/python3.8.3/lib/python3.8/lib/python3.8/site-packages/datasets/builder.py", line 1644, in _prepare_split_single datasets.builder.datasetgeneraationerror: an error occurred wile generating the dataset.

例如数据集里的问题 提供一个包含两个城市名称的列表,然后为这两个城市之间的距离提供一个近似值。 1. 北京 2. 上海 但回答的结果是一个计算步骤,不是数据集里的值

`ValueError: 130000 is not in list` ice_text.model tokenization_chatglm.py tokenizer_config.py 均为4/24下载的最新版本