Darebal/mountain-names-ner

Model Description

This model is a fine-tuned BERT model for token classification, specifically for the task of identifying different types of mountains in text. It has been fine-tuned on a custom dataset of text with mountain-related entities. The model uses the bert-base-uncased architecture and was trained using Hugging Face's Trainer API.

Evaluation Results

The model was evaluated on a validation dataset and achieved the following metrics:

Metric	Value
eval_loss	0.009353181347250938
eval_precision	0.9497716894977168
eval_recall	0.9674418604651163
eval_f1	0.9585253456221198
eval_accuracy	0.9968582275166906
eval_runtime	1.954
eval_samples_per_second	113.101
eval_steps_per_second	7.165
epoch	5.0

The evaluation was conducted on the validation dataset after 5 epochs of training.

Usage Instructions

To use the model, you can load it with the Hugging Face transformers library. Here's how to load and use the model for inference:

from transformers import BertTokenizerFast, BertForTokenClassification
from transformers import pipeline

# Load the model and tokenizer
model = BertForTokenClassification.from_pretrained("Darebal/mountain-names-ner")
tokenizer = BertTokenizerFast.from_pretrained("Darebal/mountain-names-ner")

# Create a pipeline for token classification
nlp = pipeline("token-classification", model=model, tokenizer=tokenizer)

# Example input
text = "The Everest is the tallest mountain in the world."

# Get predictions
predictions = nlp(text)
print(predictions)