Fine-tuned LoRA Token classification on distilbert

This is a fine-tuned LoRA token classifier on distilbert, designed for NER on multiple categories PERSON, ORG, CITY, STATE, CITY_STATE.

Model Details

Model Description

This model is based on distilbert/distilbert-base-uncased and fine-tuned using LoRA for token classification. The fine-tuning process adapts the model to predict tokens across 10 categories:

"O"  # Outside any named entity
"B-PER"       # Beginning of a person entity
"I-PER"       # Inside a person entity
"B-ORG"       # Beginning of an organization entity
"I-ORG"       # Inside an organization entity
"B-CITY"      # Beginning of a city entity
"I-CITY"      # Inside a city entity
"B-STATE"     # Beginning of a state entity
"I-STATE"     # Inside a state entity
"B-CITYSTATE" # Beginning of a city_state entity
"I-CITYSTATE" # Inside a city_state entity

Model Sources

Citation

If you use this model, please cite it as:

@misc{mozilla_distilbert_lora_ner,
  title       = {Fine-tuned LoRA Token Classifier on DistilBERT},
  author      = {Mozilla},
  year        = {2024},
  url         = {https://huggingface.co/Mozilla/distilbert-finetuned-LoRA-token-classifier},
  license     = {Apache-2.0}
}
Downloads last month
64
Safetensors
Model size
66.4M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Mozilla/distilbert-uncased-NER-LoRA

Quantized
(23)
this model

Dataset used to train Mozilla/distilbert-uncased-NER-LoRA

Space using Mozilla/distilbert-uncased-NER-LoRA 1