phc4valid

load albert model error

6

File "run_kbert_cls.py", line 261, in main model.load_state_dict(torch.load(args.pretrained_model_path), strict=False) File "/opt/conda/envs/phchen-k/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1044, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for Model: size mismatch...

convert_albert_from_huggingface_to_uer.py 報錯

1

Traceback (most recent call last): File "convert_albert_from_huggingface_to_uer.py", line 43, in output_model["target.sop_linear_1.weight"] = input_model["albert.pooler.weight"] KeyError: 'albert.pooler.weight' 您好, 我在使用代碼轉換hugging face model hub 之 voidful/albert_chinese_base (https://huggingface.co/voidful/albert_chinese_base )時,遇到了上述問題,想問問題出在哪?萬分感謝您

關於知識triple掛載 ,predicate True or False?

1

您好, @autoliuweijie 大大, 請問您在做NER任務時特別將predicate設置成False ,只掛載實體屬於什麼類型 ,而沒將'類別'也放進去的原因是什麼?(如下圖之慢性胃炎->疾病  `kg = KnowledgeGraph(spo_files=spo_files, predicate=False)` 在其他任務中則將predicate設置成True,是因為效能因素嗎?或有任何原因嗎? `kg = KnowledgeGraph(spo_files=spo_files, predicate=True)`

about model.bin

1

Dear @autoliuweijie , Thank you so much for your innovative study. I was wondering that if there is any chances that I change BERT to BERT-like models (etc:RoBERTa-chinese ,MacBERT). Is...

關於斷詞評估指標 evaluation metrics

1

老師們您好, 我想請問內文指出在 ASBC 4.0 Test Split (50,000 sentences) 之分數  是以(1)每一個句子斷詞後之起止區間與ground truth之起止區間所計算獲得之f1 ,加總50000句之f1後的平均  或是以(2)50000句串聯並斷完詞後之起止區間與ground truth之起止區間所計算獲得之f1 或是以上皆非正確計算方式 深怕自己有理解上的錯誤,想請教正確的實作方式,萬分感謝撥空閱讀

Other language usage

1

Hi , I really like and appreciate what you guys are doing. Is it possible to implement the method on other languages ? etc :Chinese General-usage of language model was...