---
license: apache-2.0
base_model: google/gemma-4-12B-it
library_name: transformers
tags:
  - text-generation
  - conversational
  - text-only
pipeline_tag: text-generation
---

# gemma-4-12B-it-OnlyText

Text-only causal language model derived from [google/gemma-4-12B-it](https://huggingface.co/google/gemma-4-12B-it)
by removing the vision and audio stacks (their towers/embedders and projector weights)
and the multimodal special tokens. The text backbone and LM head are preserved.

## Details

- Base model: [google/gemma-4-12B-it](https://huggingface.co/google/gemma-4-12B-it)
- Architecture: `Gemma4UnifiedForCausalLM`
- Parameters: 11.91B
- Layers: 48 · Hidden size: 3840
- MTP head: not present
- Weights: `bfloat16`

## Attribution

This model is a derivative of [google/gemma-4-12B-it](https://huggingface.co/google/gemma-4-12B-it) by the
[Google team](https://huggingface.co/google), released under the
[apache-2.0 license](https://www.apache.org/licenses/LICENSE-2.0).
All credit for the underlying weights and capabilities belongs to the original
authors; this repository only removes modalities, it does not add new training.

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("OnlyTextLLMs/gemma-4-12B-it-OnlyText")
tokenizer = AutoTokenizer.from_pretrained("OnlyTextLLMs/gemma-4-12B-it-OnlyText")
```