cdj0311

Results 8 issues of cdj0311

我的训练集中有一些词,比如“查不到”,大概出现了100次,但是在测试的时候在不加词典的情况下就始终把这个词分不出来,请问这是怎么回事?

您好,感谢分享, 请教一个多机训练问题。 使用keras和tf.distribute.experimental.MultiWorkerMirroredStrategy()进行多机训练时,batch_size=batch_size * worker_num,那么输入的数据(tfrecord格式)需要切分成worker_num份吗?如果不切分,每个worker都读取所有的数据,这种分布式策略会不会自动对数据进行分发呢?

In python, I run python test.py, but there has an error: import _CRFPP ImportError: libcrfpp.so.0: cannot open shared object file: No such file or directory

大佬好, 我用gpt2_example.py推理gpt2,生成的第1个token没问题,但把生成的token拼接到前面的序列后继续推理生成的结果就不对了, 比如我的输入是:input_ids = torch.tensor([[12166, 10699, 16752, 4454]], dtype=torch.long).to(test_device) 推理代码: for _ in range(32): res = tt_model(input_ids) # sequence_output, pooled_output gen_id = torch.argmax(res[0]) input_ids = torch.cat([input_ids, gen_id.unsqueeze(0).unsqueeze(1)], dim=-1) 生成结果:tensor([[12166, 10699,...

hi, I have trained a GPT model with 4 nodes (8 gpus per node), but when I load the checkpoint with 6 nodes, I get the follows error: ```` deepspeed.runtime.zero.utils.ZeRORuntimeException:...

I want use liblinear with python, but there find an error "LIBLINEAR library not found" with "from liblinear import *". However, the path of liblinear.dll is right, and it can...

My tree is include dict and list, for example: data1 = {"a": [{"b": []}, {"c": [{"h":[]}]}]}, data2 = {"a": [{"b": [{"m":[]}]}, {"c": [{"h":[{"k":[]}]}]}]}, the edit distance always 1. The code:...

hi, I want train a completion model include multiple lines edits, smart rewrites, how prepare the dataset format such as fill-in-the middle? thanks!