Sponsored by iMean AI Trip Planner
Toolify Toolify logo
AI Models
mmbert-base-tr-uncased-ner

akdeniz27 / mmbert-base-tr-uncased-ner

Run on huggingface.co
huggingface.co
Total runs: 20
24-hour runs: 1
7-day runs: 3
30-day runs: 3
Model's Last Updated: September 10 2025
token-classification

Introduction of mmbert-base-tr-uncased-ner

Model Details of mmbert-base-tr-uncased-ner

Turkish Named Entity Recognition (NER) Model

This model is the fine-tuned version of Multilingual ModernBERT model "jhu-clsp/mmBERT-base" using a reviewed version of well known Turkish NER dataset ( https://github.com/stefan-it/turkish-bert/files/4558187/nerdata.txt ).

Fine-tuning parameters: 

task = "ner"
model_checkpoint = "jhu-clsp/mmBERT-base"
batch_size = 8 
label_list = ['O', 'B-PER', 'I-PER', 'B-ORG', 'I-ORG', 'B-LOC', 'I-LOC']
max_length = 8192
learning_rate = 2e-5 
num_train_epochs = 5 
weight_decay = 0.01

How to use: 

from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
model = AutoModelForTokenClassification.from_pretrained("akdeniz27/mmbert-base-tr-uncased-ner")
tokenizer = AutoTokenizer.from_pretrained("akdeniz27/mmbert-base-tr-uncased-ner")
# tokenizer.model_max_length = 512 # Model max_length could be set here (max 8192 as default)
ner = pipeline("token-classification", model=model, tokenizer=tokenizer, aggregation_strategy="first")
ner("your text here")

Pls refer " https://huggingface.co/transformers/_modules/transformers/pipelines/token_classification.html " for entity grouping with aggregation_strategy parameter.

Reference test results:

  • accuracy: 0.991023766617932
  • f1: 0.9414858645627877
  • precision: 0.9397695785328861
  • recall: 0.9432084309133489

Runs of akdeniz27 mmbert-base-tr-uncased-ner on huggingface.co

20
Total runs
1
24-hour runs
3
3-day runs
3
7-day runs
3
30-day runs

More Information About mmbert-base-tr-uncased-ner huggingface.co Model

More mmbert-base-tr-uncased-ner license Visit here:

https://choosealicense.com/licenses/mit

mmbert-base-tr-uncased-ner huggingface.co

mmbert-base-tr-uncased-ner huggingface.co is an AI model on huggingface.co that provides mmbert-base-tr-uncased-ner's model effect (), which can be used instantly with this akdeniz27 mmbert-base-tr-uncased-ner model. huggingface.co supports a free trial of the mmbert-base-tr-uncased-ner model, and also provides paid use of the mmbert-base-tr-uncased-ner. Support call mmbert-base-tr-uncased-ner model through api, including Node.js, Python, http.

mmbert-base-tr-uncased-ner huggingface.co Url

https://huggingface.co/akdeniz27/mmbert-base-tr-uncased-ner

akdeniz27 mmbert-base-tr-uncased-ner online free

mmbert-base-tr-uncased-ner huggingface.co is an online trial and call api platform, which integrates mmbert-base-tr-uncased-ner's modeling effects, including api services, and provides a free online trial of mmbert-base-tr-uncased-ner, you can try mmbert-base-tr-uncased-ner online for free by clicking the link below.

akdeniz27 mmbert-base-tr-uncased-ner online free url in huggingface.co:

https://huggingface.co/akdeniz27/mmbert-base-tr-uncased-ner

mmbert-base-tr-uncased-ner install

mmbert-base-tr-uncased-ner is an open source model from GitHub that offers a free installation service, and any user can find mmbert-base-tr-uncased-ner on GitHub to install. At the same time, huggingface.co provides the effect of mmbert-base-tr-uncased-ner install, users can directly use mmbert-base-tr-uncased-ner installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

mmbert-base-tr-uncased-ner install url in huggingface.co:

https://huggingface.co/akdeniz27/mmbert-base-tr-uncased-ner

Url of mmbert-base-tr-uncased-ner

mmbert-base-tr-uncased-ner huggingface.co Url

Provider of mmbert-base-tr-uncased-ner huggingface.co

akdeniz27
ORGANIZATIONS
huggingface.co

Other API from akdeniz27

 huggingface.co
akdeniz27/ppo-Huggy

Total runs: 30
Run Growth: -54
Growth Rate: -180.00%
Updated:July 12 2023
huggingface.co
akdeniz27/taxi-v3

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:July 17 2023