ULMFiT - German

[jolackner (Johannes Lackner)]

Thank you for sharing this! Reading your blog post re: training another model with more data - Are you considering training a German GPT-2 (345M)? That could take Natural language generation in German (which seems hard/unfeasible with BERT and is generally lagging behind English NLG) to a new level.

[malte.pietsch]

Our priority for now is training more BERT models on larger datasets (incl. domain specific ones) and simplify the usage for standard downstream tasks like document classification, NER, QA …

But maybe we afterwards move on to GPT-2 (or whatever NLG model is out there by then).

[piotr.czapla]

Have you considered getting the model exposed through pytorch.hub either through fastai repo or huggingface?

It would be nice if someone could simply state:
tokenizer = torch.hub.load('huggingface/pytorch-pretrained-BERT', 'bertTokenizer', 'bert-de-deepset-base', do_basic_tokenize=True, do_lower_case=False)

[faib (Fabian)]

From my understanding there is no pretrained german language model for ULMFiT working for the current fastai v1.0.54?

Even @jyr1’s model gives me an error when I try to load it:

weights='30k-pre-ger'
vocs='30k-pre-ger-itos'
learn = language_model_learner(data_lm, AWD_LSTM, pretrained=False, drop_mult=0.5, pretrained_fnames=[weights, vocs])

[jolackner (Johannes Lackner)]

That’s due to all language model shapes being divisible by 8 as of fastai 1.0.53 by default (reason: half precision training is much faster this way). Thankfully, Sylvain Gugger posted a workaround here:

Language_model_learner not working as before?

Your issue comes from the breaking change in fastai v1.0.53 making the hidden size a multiple of 8 (1152 instead of 1150) and your pretrained weights have the old size (1150). Just pass along this config to deal with it: config = awd_lstm_lm_config.copy() config['n_hid'] = 1150 learn = language_model_learner(data_lm, AWD_LSTM, config=config, pretrained_fnames=[FILE_LM_ENCODER, FILE_ITOS], drop_mult=0.3)

[faib (Fabian)]

I was completely unaware of that. Will try today, thank you!

[felixsmueller (felix müller)]

Hi
Is there a trained German model in the meantime that can be downloaded somewhere or will the ‘official’ German model come out soon (in the official model zoo)?
Regards, Felix

[jolackner (Johannes Lackner)]

Hi @felixsmueller. @jyr1 trained a language model a while back that works well for me:

ULMFiT - German

About 12 hours on a Tesla P100 (Google Cloud). To be honest I don’t have much other details as I was merely interested in sentiment classification and not the preliminary steps. Anyways, here’s the link, the vocab is 30k. You can load the model directly in language_model_learner using the pretrained_fnames argument. https://drive.google.com/open?id=1gkuY3Tz6LBmcehAnZ95jssV80CBQh7L1

If using a recent fastai version (1.0.53 and later), you will have to read in the weights according to Sylvain Gugger’s workaround (see post a bit further up).

[felixsmueller (felix müller)]

FILE_LM_ENCODER

Thanks a lot.
Just some more descriptions for newbies like me:
Download the language model files (from https://drive.google.com/open?id=1gkuY3Tz6LBmcehAnZ95jssV80CBQh7L1) and store them into your Google drive account.
#Then the following code allows to access your Google drive:
from google.colab import drive
drive.mount(’/content/gdrive’, force_remount=True)
root_dir = “/content/gdrive/My Drive/”
base_dir = root_dir + ‘Colab Notebooks/FastAIGermanModel’ #Adapt path
#The following code then reads in the model:
FILE_LM_ENCODER = base_dir + ‘/30k-pre-ger’
FILE_ITOS = base_dir + ‘/30k-pre-ger-itos’
config = awd_lstm_lm_config.copy()
config[‘n_hid’] = 1150
learn = language_model_learner(data_lm, AWD_LSTM, config=config, pretrained_fnames=[FILE_LM_ENCODER, FILE_ITOS], drop_mult=0.3)