zhihao-chen

基于CPT-Large模型finetune CPTForConditionalGeneration之后，预测出的结果跟输入一模一样。这是为什么呢？decoder的输出跟输入是一模一样的

'BertModel' object has no attribute 'set_flag'

4

具体报错是： File "/data2/work2/chenzhihao/NLP/nlp/sentence_transformers/SentenceTransformer.py", line 594, in fit loss_value = loss_model(features, labels) File "/root/anaconda3/envs/NLP_py39/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/data2/work2/chenzhihao/NLP/nlp/sentence_transformers/losses/AdvCLSoftmaxLoss.py", line 775, in forward rep_a_view1 = self._data_aug(sentence_feature_a, self.data_augmentation_strategy_final_1,...

binascii.Error: Incorrect padding

4

### Description 报错： Traceback (most recent call last): File "/root/work2/work2/chenzhihao/kefu_dialogue/examples/finetune_chatyuan_by_flagai.py", line 360, in main() File "/root/work2/work2/chenzhihao/kefu_dialogue/examples/finetune_chatyuan_by_flagai.py", line 352, in main trainer.train(model, File "/root/anaconda3/envs/flagai/lib/python3.9/site-packages/flagai/trainer.py", line 499, in train model, optimizer, _,...

Adafactor is not a supported DeepSpeed Optimizer

2

### System Info 我按照example中的finetune huggingface t5_11b的示例在其它数据集中执行，但是出现以下错误。 /root/work2/work2/chenzhihao/DeepSpeed/deepspeed/runtime/engine.py:1008 in _do_sanity_check │ │ │ │ 1005 │ │ │ │ 1006 │ │ if not self.client_optimizer: │ │ 1007 │ │ │...

GLM架构上是与T5类似的，因此理论上是能做机器翻译任务的吧？那在机器翻译任务上finetune，也是像T5一样需要设计prefix吗？

按照示例运行报错

7

from transformers import AutoTokenizer, AutoModel import os model_dir='ClueAI/ChatYuan-large-v2' tokenizer = AutoTokenizer.from_pretrained(model_dir) # 速度会受到网络影响，网络不好可以使用下面高级参数配置方式 model = AutoModel.from_pretrained(model_dir, trust_remote_code=True) history = [] print("starting") while True: query = input("\n用户：") if query == "stop":...