FrontiersMind/NandiBERT-150M

fill-mask model by FrontiersMind

Open original source ↗

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Hugging Face | GitHub | Launch Blog | Website | Technical Report (Coming Soon) License: Apache-2.0 | Authors: FrontiersMind NandiBERT is a family of open bidirectional encoders that reach state of the art in both English and Indic languages at their size, where earlier encoders were strong in one and weak in the other. For NandiBERT-150M, the parameter count is the encoder that you fine-tune (146M). The checkpoint also stores the untied MLM output layer (77M), so the model file holds 224M parameters. Note: NandiBERT is pre-trained on 13 Indic languages in native script: Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Nepali, Odia, Punjabi, Tamil, Telugu and Urdu. Note: Model results are the average of 3 different seeds. NandiBERT-150M loads with Hugging Face transformers 5.x using trustremotecode=True. AutoModelForSequenceClassification and AutoModelForTokenClassification reuse the pretrained MLM head. The encoder output goes through the MLM head…

FrontiersMind/NandiBERT-150M on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-22T09:53:33.246Z

Inside the original model card — Document outline
  1. NandiBERT-150M
  2. Description
  3. Benchmark Results
  4. Indic Benchmarks
  5. English Benchmarks
  6. Usage
  7. Fine-tuning
  8. Citation

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Documentation belongs to its respective authors. Reported project/model license: apache-2.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

FrontiersMind/NandiBERT-150M is a fill-mask model repository published by FrontiersMind on Hugging Face. The source reports the transformers library.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task
fill-mask
Library
transformers
Recent downloads (30 days)
173
Cumulative likes
31
Hugging Face trending score
28
Reported safetensors parameters
223,742,464
Architecture
NandiForMaskedLM
License
apache-2.0
Access
Not gated by Hugging Face
Created
2026-11-18T16:13:10.000Z
Last modified
2026-11-20T19:18:20.000Z

Compatibility and lineage

Reported languages: en, hi, mr, pa, ta, te, kn, ml, bn, gu, as, or, ur, ne, ar, id, ms

Base-model lineage was not included.

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-22T07:01:15.786Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source

Related models

google-bert/bert-base-uncased

FacebookAI/xlm-roberta-base

FacebookAI/roberta-base

microsoft/mdeberta-v3-base

distilbert/distilbert-base-uncased

FacebookAI/roberta-large