---
pipeline_tag: fill-mask
license: apache-2.0
base_model: answerdotai/ModernBERT-base
library_name: kerasformers
tags:
- keras
- kerasformers
- modernbert
- fill-mask
- text-encoder
- arxiv:2412.13663
- pytorch
- jax
- tf
---

# Run ModernBERT with Keras 3: JAX, PyTorch, or TensorFlow

[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-black?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-ModernBERT-blue)](https://imvision12.github.io/KerasFormers/modernbert/)

# kerasformers/modernbert_base

Paper: [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder (arXiv:2412.13663)](https://arxiv.org/abs/2412.13663) · [HF Papers](https://huggingface.co/papers/2412.13663)

ModernBERT is Answer.AI / LightOn's modernized bidirectional transformer text encoder: rotary position embeddings, attention that alternates between a global (full) layer and local sliding-window layers, GeGLU feed-forwards, and pre-LayerNorm, with an 8192-token context. Byte-level BPE tokenizer; mask token `[MASK]`. No token-type ids.

For more details on the model, please go to the upstream [model card](https://huggingface.co/answerdotai/ModernBERT-base).

Pure-**Keras 3** conversion of [`answerdotai/ModernBERT-base`](https://huggingface.co/answerdotai/ModernBERT-base) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.

This is a **fill-mask / encoder** checkpoint (`ModernBertMaskedLM`, modernbert_base). Task heads (sequence / token classify, QA, multiple choice) load via `hf:` fine-tunes.

## ✨ Quick start (fill-mask)

```python
import os
os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"

from kerasformers.models.modernbert import ModernBertMaskedLM, ModernBertTokenizer

mlm = ModernBertMaskedLM.from_weights("kerasformers/modernbert_base")
tokenizer = ModernBertTokenizer.from_weights("kerasformers/modernbert_base")

inputs = tokenizer("The capital of France is [MASK].")
logits = mlm(inputs)  # (1, L, vocab_size)
mask = int((inputs["input_ids"][0] == tokenizer.mask_token_id).argmax())
print(tokenizer.decode([int(logits[0, mask].argmax())]))
```

Load any ModernBERT variant the same way with `from_weights("kerasformers/<variant>")`:

| Variant | Hub | layers | embed_dim |
|---|---|---|---|
| `modernbert_base` | [`kerasformers/modernbert_base`](https://huggingface.co/kerasformers/modernbert_base) | 22 | 768 |
| `modernbert_large` | [`kerasformers/modernbert_large`](https://huggingface.co/kerasformers/modernbert_large) | 28 | 1024 |

## Available classes

Load any of these from this repo with `from_weights("kerasformers/modernbert_base")` (or on the fly via the `hf:` prefix). The pretrained backbone is shared; task heads not stored in this checkpoint start randomly initialized, ready for fine-tuning (or load a `hf:` fine-tune).

| Class | Task |
|---|---|
| `ModernBertModel` | Encoder backbone |
| `ModernBertMaskedLM` | Masked language modeling (fill-mask) |
| `ModernBertSequenceClassify` | Sequence classification |
| `ModernBertTokenClassify` | Token classification (NER / POS) |
| `ModernBertQnA` | Extractive question answering |
| `ModernBertMultipleChoice` | Multiple choice |

```python
from kerasformers.models.modernbert import ModernBertSequenceClassify
model = ModernBertSequenceClassify.from_weights("kerasformers/modernbert_base")
```

## Tips

- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
- Prefer `ModernBertTokenizer.from_weights(...)` so tokenization matches.
- Use `[MASK]` (not `<mask>`).
- ModernBERT has no token-type ids; the tokenizer emits only `input_ids` / `attention_mask`.
- See [ModernBERT docs](https://imvision12.github.io/KerasFormers/modernbert/) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
- Community / upstream safetensors still work via the `hf:` prefix, e.g. `ModernBertMaskedLM.from_weights("hf:answerdotai/ModernBERT-base")`.

## Special Thanks

A huge thank you to the Answer.AI and LightOn authors for creating and releasing ModernBERT.

License: Apache 2.0.