Stack Overflow
Stack Overflow

Questions tagged [allennlp]

An open-source NLP research library, built on PyTorch

An Apache 2.0 NLP research library, built on PyTorch, for developing state-of-the-art deep learning models on a wide variety of linguistic tasks.

Quick Links

210 questions
37
votes
17 answers

Message "note: This error originates from a subprocess, and is likely not a problem with pip"

While downloading pip install allennlp==1.0.0 allennlp-models==1.0.0, I faced this problem: [6 lines of output] running bdist_wheel running build running build_py running build_ext building…
Ahmad Sadek Albasatneh
  • 475
  • 2
  • 4
  • 4
20
votes
1 answer

pytorch delete model from gpu

I want to make a cross validation in my project based on Pytorch. And I didn't find any method that pytorch provided to delete the current model and empty the memory of GPU. Could you tell that how can I do it?
Charmander
  • 201
  • 1
  • 2
  • 3
5
votes
1 answer

How to load a finetuned sciBERT model in AllenNLP?

I have finetuned the SciBERT model on the SciIE dataset. The repository uses AllenNLP to finetune the model. The training is executed as follows: python -m allennlp.run train $CONFIG_FILE --include-package scibert -s "$@" After a successful…
Tomaž Bratanič
  • 6,319
  • 2
  • 18
  • 31
5
votes
1 answer

Fluctuating loss during training for text binary classification

I'm doing a finetuning of a Longformer on a document text binary classification task using Huggingface Trainer class and I'm monitoring the measures of some checkpoints with Tensorboard. Even if the F1 score and accuracy is quite high, I have…
Paolo Magnani
  • 549
  • 4
  • 14
5
votes
1 answer

pip - Installing specific package version does not work

I was trying to install a library (allennlp) via pip3. But it complained about the PyTorch version. While allennlp requires torch=0.4.0 I have torch=0.4.1: ... Collecting torch==0.4.0 (from allennlp) Could not find a version that satisfies the…
MBT
  • 21,733
  • 19
  • 84
  • 102
4
votes
1 answer

Multi-GPU training of AllenNLP coreference resolution

I'm trying to replicate (or come close) to the results obtained by the End-to-end Neural Coreference Resolution paper on the CoNLL-2012 shared task. I intend to do some enhancements on top of this, so I decided to use AllenNLP's CoreferenceResolver.…
KurtMica
  • 992
  • 7
  • 16
4
votes
1 answer

Cant install allennlp with pip on mac

I am trying to install allennlp on my mac. I have tried installing macOS headers which solved the missing headers problem but now i am experiencing new problems. The error when i run pip install allennlp: Running setup.py bdist_wheel for jsonnet…
Saket Khandelwal
  • 61
  • 3
4
votes
0 answers

Maintaining packages with different versions in one python environment

I need an older version of torch (0.5.0) for a certain library (allennlp==0.7.2). But I already have an existing torch version (1.0.0) as required by flair and other libraries. How do I cater to different requirements of the same package of multiple…
Hit
  • 239
  • 2
  • 5
3
votes
1 answer

Google Colab recently raise error ModuleNotFoundError: No module named 'google.cloud.storage.retry'

My code just worked properly on local and colab, however recently faced the following error on colab. I use google colab to run my code. The allennlp package was installed. Error when run code
Amir Sartipi
  • 91
  • 1
  • 8
3
votes
1 answer

AllenNLP DatasetReader.read returns generator instead of AllennlpDataset

While studying AllenNLP framework (version 2.0.1), I tried to implement the example code from https://guide.allennlp.org/training-and-prediction#1. While reading the data from a Parquet file I got: TypeError: unsupported operand type(s) for +:…
Ido
  • 573
  • 4
  • 11
3
votes
0 answers

AllenNLP Semantic Role Label - SRLBert Error

I am trying to run the AllenNLP demo https://demo.allennlp.org/semantic-role-labeling. When I run the command line or the Python version via Juptyer I get the error mentioned below. I have installed the required libraries? pip install…
scarpacci
  • 8,957
  • 16
  • 79
  • 144
3
votes
1 answer

configuration file allenNLP

I am trying to understand how to build configuration file for our experiements let us take this example from the AllenNLP documentation training and prediction in particular this snippet From where we got "token_embedders"? shouldn't be "basic" as…
Arij Aladel
  • 356
  • 1
  • 3
  • 10
3
votes
1 answer

Allennlp ConfigurationError: key "matrix_attention" is required at location "model."

I'm new to Allennlp, and this is my first time trying it out. I already installed all the required libraries !pip install allennlp !pip install --pre allennlp-models and my code should be fine too, but I still get this error message saying:…
Unterbelichtet
  • 628
  • 2
  • 7
  • 18
3
votes
1 answer

Using spaCy models with AllenNLP Interpret or Textattack

AllenNLP Interpret and Textattack are supposed to "attack" models to figure out why they generate their output. I have mostly used spaCy to train my models and would like to try either of the frameworks and see if they give me a better understanding…
Kaisa K
  • 31
  • 1
3
votes
0 answers

Using Elmo models to predict the masked word in a sentence

I have a homework which requires me to build an algorithm that can guess a missing word from a sentence. For example, when the input sentence is : " I took my **** for a walk this morning" , I want the output to guess the missing word(dog). My…
ihatepointers
  • 43
  • 6
1
2 3
…
13 14