-
Hey all,
I am trying to use the ` --not_predict_token` to remove a certain token from predictions which is the - [CLS] token. The issue is that while decoding on news texts it produces outputs like …
-
## ❓ How Cased/Uncased processing matter for Summarization Task?
Hi, I noticed the fairseq use Cased for summarization. What's more, UniLM also use Cased data. While many previous SOTA works (like…
-
Hi,
I followed the instructions for fine-tuning UniLM v1.2 on XSum task.
Specifically I used the following commands:
```
python -m torch.distributed.launch --nproc_per_node=4 run_seq2seq.py …
-
-
-
/kind bug
**What steps did you take and what happened:**
[A clear and concise description of what the bug is.]
```
curl -v --connect-timeout 600 -H "Host: kfserving-custom-model.aasdev.example.c…
-
-
作者你好，请问论文给出的结果是最后一个epoch的评估结果，还是每个epoch dev集最高的测试结果呢？另外如果是第一种random seed有放开么？感谢~
-
I set up the model for training for document classification task. Followed the instructions on README page. However, usually a minute or so into training, I would get an error as below:
我按照README把数据和…
-
When running the decode, I expected the output to resemble something close to target in the input file. I've created iput.json as shown in the README.md in s2s-ft:
```
{"src": "Messages posted on …