flair
flair copied to clipboard
flairNLP
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Hi there, I would like to use SWA while training my model. Currently SWA is implemented in flair with the `torchcontrib` package. However this is now deprecated as SWA is...
Hi there, **Background:** I am using a few-shot TARS model to label sentence sentiment as one of 3 possible classes: class_a, class_b, or class_c. **Questions 1:** If my sentences are...
I'm trying to install Flair in my venv in PyCharm, but it tells me to download Visual C++. I have already installed the ditributives of 14.32.31332 version but it still...
**Describe the bug** I am trying to install flair on my MacBook m1 air. I have used both `pip install flair` and `pip3 install flair but it fails everytime. Here...
I am using FLAIR for text classification ("TextClassifier") with RoBERTa. My dataset just contains about 2000 instances but the text instances themselves are fairly long, i.e. longer than 512 tokens....
Torch has just released MAC M1 support using mps device. I want to know if flair will support it. I tried setting the flair.device manually to mps but it failed...
Dear Flair developers, I try to process the biomedical NER datasets used in HunFlair and I use the code from flair/datasets/biomedical.py. While downloading the datasets, some requsts errors occur. I'm...
All other settings are the same (same data, same code etc), but using "make_label_dictionary" and "make_tag_dictionary" to create "tag_dictionary" for NER model give completely different results. I am training a...
adds ACE, from this repo: https://github.com/Alibaba-NLP/ACE currently not tested on larger training, but at least it runs through when using CONLL_03 downsampled to 0.005 on each dataset. ## Inner working:...
**Describe the bug** `ModelTrainer.train` method fails with error ```UnboundLocalError: local variable 'train_part_eval_result' referenced before assignment``` when used with tensorboard. This error is simply due to a forgotten tab in the...
