BitcoinKing

I am trying to use code with my dataset (training now goes). For this i am trying to replicate structure of Ubuntu Dialog Corpus (UDC) from https://arxiv.org/pdf/1506.08909v3.pdf In you article...

No network image produced

4

When i run hijackers.py file in Pycharm i dont see any image. Here is output: D:\WinPython-32bit-2.7.5.1\python-2.7.5\python.exe "F:/Python/Graph packages/SNABook-master/chapter4/hijackers.py" drawing nodes... {'93_Penn': 'g', '175_WTC South': 'r', 'None': 'b', '77_Pentagon': 'm', '11_WTC...

How to train new SRL model ?

4

Hi, deepnl is cool, but i cannot find good tutorial on how to train my custom Semantic Role labeling model (language other than english). I have read presentation and article...

Using GPT2-xl in train and interact

1

Hi, i realized that there are a new gpt2-xl pretrained model appears in list here: https://huggingface.co/transformers/pretrained_models.html Is it possible to train with this model and then interact with result ?

Fine-tune with own dataset - how to multi-turn ?

2

When i run `python demo.py` a got an advice how to train model with own data: `python LSP_train.py --model_name_or_path /home/joo/Docs/LocalRepository/DialoGPT/models/small --init_checkpoint /home/joo/Docs/LocalRepository/DialoGPT/models/small/pytorch_model.bin --train_input_file /home/joo/Docs/LocalRepository/DialoGPT/data/train.128len.db --eval_input_file ./data/dummy_data.tsv --output_dir /home/joo/Docs/LocalRepository/DialoGPT/models/output_model --seed 42...

User session in Telegram supported ?

2

Hi, cool work. Does it support a session for every user that talk to bot in Telegram? This is vital, because we should store conversation history for every user separated....

How to get class for given text input?

7

Could you provide some example code how to get class output for given text input? I was able to get all code working with ./data/small_samples.json but output is accuracy percent...

Error "not enough values to unpack" on predict

1

When do predict i have got error after 7200 step: ``` CRITICAL:root:Saved model d:\Django\multi-class-text-classification-cnn\trained_model_1485372325\checkpoints\model-7200 at step 7200 CRITICAL:root:Best accuracy 0.8768386935926203 at step 7200 Traceback (most recent call last): File "train.py",...

Support other than english languages

1

What's your advice on how to implement this repository with russian language?

w2v не работает, замены не подходят

3

Не получилось сгенерировать файл с помощью https://gist.github.com/Koziev/e39689adec30ae5bf6afaa1ca47c08e5 В итоге вытащил его из образа докер.