0

希望你们都做得很好，我正在微调 GPT 2 模型以根据内容生成标题，在处理它时，我创建了一个简单的 CSV 文件，其中只包含标题来训练模型，但是在输入这个模型时到 GPT 2 进行微调我在 () 10 steps=1000, 11 save_every=200, ---> 12 sample_every=25) 中收到以下 ERROR , JSONDecodeError Traceback (last recent call last) #steps is max number of training步骤 13 14 # gpt2.generate(sess)

    3 frames
    /usr/lib/python3.7/json/__init__.py in loads(s, encoding, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw)
        336         if s.startswith('\ufeff'):
        337           s = s.encode('utf8')[3:].decode('utf8')
    --> 338             # raise JSONDecodeError("Unexpected UTF-8 BOM (decode using utf-8-sig)",
        339             #                       s, 0)
        340     else:
    
    JSONDecodeError: Unexpected UTF-8 BOM (decode using utf-8-sig): line 1 column 1 (char 0)
    
    Below is my code for the above :
    
    import gpt_2_simple as gpt2
    
    model_name = "120M" # "355M" for larger model (it's 1.4 GB)
    gpt2.download_gpt2(model_name=model_name)   # model is saved into current directory under /models/117M/
    sess = gpt2.start_tf_sess()
    
    gpt2.finetune(sess,
                  'titles.csv',
                  model_name=model_name,
                  steps=1000,
                  save_every=200,
                  sample_every=25)   # steps is max number of training steps
    
    I have tried all the basic mechanism of handing UTF -8 BOM but did not find any luck ,Hence requesting your help .It would be a great help from you all .
4

1 回答 1

0

尝试更改型号名称，因为我看到您输入 120M，而 gpt2 型号称为 124M

于 2021-05-26T22:50:14.690 回答