gemma-3-4b-it-pms-16384

This model is a 14.63% smaller version of google/gemma-3-4b-it optimized for Piedmontese language via vocabulary size reduction using the trimming method.

This trimmed model should perform similarly to the original model with only 16,384 tokens and a much smaller memory footprint. However, it may not perform well for other languages as tokens not commonly used in Piedmontese were removed from the vocabulary.

Model Statistics

Metric	Original	Trimmed	Reduction
Vocabulary size	262,144 tokens	16,384 tokens	93.75%
Model size	4,300,079,472 params	3,670,770,032 params	14.63%

Mining Dataset Statistics

• Number of texts used for mining: 200,000 texts
• Dataset: Lumberjackk/fineweb-2-trimming

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "AlphaEdge-AI/gemma-3-4b-it-pms-16384"

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

prompt = "Your prompt in Piedmontese."
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

@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},
}