license: apache-2.0
Nikhitha Telugu Dataset Model Model ID: Nikitha-logics/Nikhitha_telugu_dataset_model
Model Type: ALBERT-based Language Model
License: Apache-2.0
Model Overview The Nikhitha Telugu Dataset Model is an ALBERT-based language model trained on a Telugu language dataset. ALBERT (A Lite BERT) is a transformer-based model designed for natural language processing tasks, optimized for efficiency and performance.
Model Details Model Size: 33.2 million parameters
Tensor Type: Float32 (F32)
Format: Safetensors
Usage To utilize this model in your projects, you can load it using the Hugging Face Transformers library:
from transformers import AlbertTokenizer, AlbertForMaskedLM
Load the tokenizer
tokenizer = AlbertTokenizer.from_pretrained("Nikitha-logics/Nikhitha_telugu_dataset_model")
Load the model
model = AlbertForMaskedLM.from_pretrained("Nikitha-logics/Nikhitha_telugu_dataset_model")