Added requirements.txt file, Added dockerfile gpu cuda 10.2 [WIP]

KeremZaman / semantic-sh

semantic-sh is a SimHash implementation to detect and group similar texts by taking power of word vectors and transformer-based language models (BERT).

MIT License

24 stars 3 forks source link

Added requirements.txt file, Added dockerfile gpu cuda 10.2 [WIP] #2

Closed ghost closed 4 years ago

ghost commented 4 years ago

support for cpu and gpu (cuda 10.2)
added requirements.txt file

ghost commented 4 years ago

For now, I have the following error when I run:

$ docker run -ti -p 4000:4000 semantic-sh:latest --port=4000
Exception: To use fasttext embeddings, model_path must be given.

Is there a way to load the model while starting the server ?

Cheers, X