metadata
license: apache-2.0
metrics:
- f1
- accuracy
pipeline_tag: token-classification
About
This model is fine-tuned https://huggingface.co/dslim/bert-base-NER for mountain names recognition. Keep in mind, that this model uses 2 less layers, than the original due to lack of GPU memory.
You can find more info in my github repo
Dataset
It was trained using ~150 samples of created dataset by ChatGPT in NER type.
How to use
You can use this model with Transformers pipeline for NER.
from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained('Strongich/bert-english-ner-mountain')
model = AutoModelForTokenClassification.from_pretrained('Strongich/bert-english-ner-mountain')
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
example = "The sun dipped below the horizon, casting a warm glow upon the rugged slopes of Mount Everest."
ner_results = nlp(example)
print(ner_results)