zhangatao

如果数据量比较大的话，还可以使用D2RQ吗

2

另外请问如何使用d2rq将hive中的数据转换成rdf的格式？

Hello, frame-based features, are you tfrecord formed through MediaPipe or based on https://github.com/google/youtube-8m/blob/master/feature_extractor/README.md. For example, if I train a classifier through the 1.53t frame feature, when I want to predict...

结果

2

你好，readme提到的0.81结果，指的是线上还是线下呀

Hello, I am very happy that you can open the code. I have a problem now. Now every time I make a query, you have to establish a connection here....

灾难性遗忘

5

请问各位大佬，你们在用自己的数据继续训练Plus模型，得到的内容会出现模型通用能力变差的情况吗

from transformers import AutoTokenizer, AutoModel model_med = AutoModel.from_pretrained("./chatglm-6b-med/", trust_remote_code=True) File ~/.cache/huggingface/modules/transformers_modules/modeling_chatglm.py:818, in ChatGLMModel.__init__(self, config, empty_init) 816 self.hidden_size_per_attention_head = self.hidden_size // self.num_attention_heads 817 self.position_encoding_2d = config.position_encoding_2d --> 818 self.pre_seq_len = config.pre_seq_len...