tner
tner copied to clipboard
asahi417
Language model fine-tuning on NER with an easy interface and cross-domain evaluation. "T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition, EACL 2021"
Hello and thank very much for the new TNER-Version. :) It seems like the old syntax/bibs (e.g. "from tner import TrainTransformersNER") have been discontinued in the new release? (btw: you...
i enabled more variations for gridsearch and the last step of training crashes now (started this twice in a row to confirm). Before it worked just fine, when i set...
Hello, I have notice that if a work ends with a punctuation mark, the punctuation mark is included as as part of the token. Is there a way to prevent...
Hello! I was wondering if you planned at some point to integrate the possibility to export the trained models in ONNX format in order to use them into an ONNX...
``` searcher = GridSearcher( checkpoint_dir='./ckpt_xlmr_naamapadam_ta', dataset='ai4bharat/naamapadam', # either of `dataset` (huggingface dataset) or `local_dataset` (custom dataset) should be given dataset_name='ta', model="xlm-roberta-base", # language model to fine-tune epoch=10, # the total...
Hi @asahi417, I have an issue with AllenNLP as a requirement. Indeed, AllenNLP brings some version-conflicts with other requirements of my project. In this case, it is preferable to drop...
Just experimenting with this. Tried to install tner and load model. getting error for tokenizer file not found. same error when trying to use transformers lib here https://huggingface.co/tner/deberta-v3-large-fin `--------------------------------------------------------------------------- Exception...
I understand downloading the model once. It gets stored in the cache and is available for the user in that session. But I want to know how to use the...
The library should support using any HF data set, just provide an option to add the relevant column names, the feature specification of the HF data set already includes a...
