-
Test {'rouge-1': {'f': 0.47346011281155474, 'p': 0.4381161507283877, 'r': 0.5239694254911272}, 'rouge-2': {'f': 0.21751781836114528, 'p': 0.21087599615939312, 'r': 0.2522172885765042}, 'rouge-l': {'f'…
PYMAQ updated
3 years ago
-
I tried to use en-zh data in bertNMT , but I got the problem in architectures match.
**My env :**
cuda 9.0
pytorch 1.0.0
python 3.6
**My Preprocess :**
token / clean and generate bpe …
-
Hi all helpful folks,
I met this error message:
`IndexError: list index out of range`
while doing inference:
`python translate.py -batch_size 2 -model models/_step_X.pt -src dataset/debug_sents.tx…
-
There is a board on ESP32. Compiled the firmware based on Marlin 2.0.9 and Esp3dlib. But there is no connection between the WEB interface and the firmware. A similar GR BL firmware works on this boar…
-
Hi there, question about fairseq NMT model ([FSMT](https://huggingface.co/transformers/model_doc/fsmt.html)) conversion.
I tried to convert my own fairseq-nmt model ([`transformer_wmt_en_de`](https…
-
I try to use a pretrain XLM with my own code, and it fail to train. So I try to use the source code and pretrained BERT from your url in the code, and it also get this error.
Is there anything should…
-
I using cura 4.9 now and every time i put in a new file to slice cura crashes.
windows 10
ender 3 v2
-
## 🐛 Bug
I have a Python module with several subclasses of `FairseqModel`, `FairseqEncoder`, etc, and configs I registered with the decorators `register_model`, `register_model_architecture`, etc. …
-
Hello
I'm trying to finetune the provided pretrained model transformer.wmt19.de-en from the paper(Facebook FAIR’s WMT19 News Translation Task Submission).
However, I cannot find the correct archi…
Sohyo updated
4 years ago
-
## 🐛 Bug
### To Reproduce
Steps to reproduce the behavior (**always include the command you ran**):
1. Run cmd '....'
- Train a transformer model with `share-all-embeddings` flag
- ru…