Liu Xiaochen

Issue when using corenlp for processing large corpus

3

I divided the large English corpus into several subsets and ran multiple CorenLp commands simultaneously, but the following error always occurs after a period of time: """ Exception in thread...

In 《attention is all you need》，lrate in noam decay they used is formulated as： "lrate = d−0.5 · min(step_num−0.5, step_num · warmup_steps−1.5)" But in your code，I found there is an...

RuntimeError: probability tensor contains either inf, nan or element < 0

2

在A100上进行batch测试时没有问题，换到A10上会报错，打印出来next token logits，padding部分对应的输出值是nan。采用的是left padding，pad值为0，请问这是什么原因导致的呢？ infer代码： messages = ['' + f"原始输入文本" + '' for data in messages] res = tokenizer(messages, padding=True) input_ids_list = res['input_ids'] input_ids = torch.LongTensor(input_ids_list).to(model.device) outputs = model.generate(input_ids=input_ids) 报错：