---
language: fin
license: gemma
tags:
  - trimmed
  - gemma
  - gemma-3
base_model: google/gemma-3-1b-it
base_model_relation: quantized
datasets:
  - Lumberjackk/fineweb-2-trimming
---

# gemma-3-1b-it-fin-32768

This model is a **26.43% smaller** version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it) optimized for Finnish language via vocabulary size reduction using the [trimming](https://huggingface.co/blog/introduction-to-trimming) method.

This trimmed model should perform similarly to the original model with only **32,768 tokens** and a much smaller memory footprint. However, it may not perform well for other languages as tokens not commonly used in Finnish were removed from the vocabulary.

## Model Statistics

| Metric | Original | Trimmed | Reduction |
|--------|----------|---------|-----------|
| **Vocabulary size** | 262,144 tokens | 32,768 tokens | **87.50%** |
| **Model size** | 999,885,952 params | 735,644,800 params | **26.43%** |

## Mining Dataset Statistics

- **Number of texts used for mining**: 200,000 texts
- **Dataset**: [Lumberjackk/fineweb-2-trimming](https://huggingface.co/datasets/Lumberjackk/fineweb-2-trimming)

## Usage
```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "lbourdois/gemma-3-1b-it-fin-32768"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "Your prompt in Finnish."
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(**model_inputs, max_new_tokens=256)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):]
response = tokenizer.decode(output_ids, skip_special_tokens=True)
print(response)
```

## Citation

#### Gemma 3
```bibtex
@misc{gemmateam2025gemma3technicalreport,
      title={Gemma 3 Technical Report},
      author={Gemma Team},
      year={2025},
      eprint={2503.19786},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2503.19786},
}
```