JBoRu

hello, i want to ask why the input word embeddings shape is (seq, batch_size, emb_dim)? i think it is should be (batch_size, seq_len, emb_dim). The batch_size represent the number of...

how to test and evaluate?

1

Hi, Thanks for your implementation for leakgan. But i don't konw what your dataset, so please explaining your dataset in data/ , and then, after training, how can i test...

why can't use the gpu to train?

4

Hello, when i use the command-- "CUDA_VISIBLE_DEVICES=0 python train.py --domain res_15" to run the process. First,it occurs the warning-- "UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape....

Hi, This code can't reproduce your paper results on webqsp. I find some other researchers also can't reproduce. Please give the solutions. Thanks!

The Training time too long

2

Hi, Thanks for your contributions, when i use your command "sh WBQ_Runner.sh" to train the model without database dump, I find the batch_size is 1 and the training time too...

what mean the "Language model objective"

2

Excuse me, Thanks for your work on implement this code, and after reading your code, i'm confused about the two commands meansing as follows: ``` For Bi-HRED + Language model...

Hi, Thanks for your meaningful works, i'm sorry to ask you about how to preprocess our data, which consist of the amr parsing result by using "stog", the sample as...

The LoRA hyper-parameters?

1

Hi, What are the hyper-parameters of rank and alpha?

looking forward for code releasing~

1

Hi, Congratulations on such interesting work! I'm looking forward to the relevant code, dataset.

### Describe the feature 目前评测多个数据集时，如果不使用vllm，只能在模型测添加batch_size，但是有的数据集较长，有的较短，同样的batch_size可能会利用gpu不充分，如何针对数据集设置batch_size。 ### Will you implement it? - [ ] I would like to implement this feature and create a PR!