Modelpublic

alphaedge-ai/Qwen3-1.7B-hrv-32768

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face

0likes9downloads

Model Card

Qwen3-1.7B-hrv-32768

This model is a 24.02% smaller version of Qwen/Qwen3-1.7B optimized for Croatian language via vocabulary size reduction using the 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 the selected languages were removed from the vocabulary.

Model Statistics

Metric	Original	Trimmed	Reduction
Vocabulary size	151,936 tokens	32,768 tokens	78.43%
Model size	2,031,739,904 params	1,543,627,776 params	24.02%

Mining Dataset Statistics

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

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "alphaedge-ai/Qwen3-1.7B-hrv-32768"

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

# prepare the model input
prompt = "Your prompt in Croatian."
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# conduct text completion
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() 

# parsing thinking content
try:
    # rindex finding 32767 (</think>)
    index = len(output_ids) - output_ids[::-1].index(32767)
except ValueError:
    index = 0

thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("
")
content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("
")

print("thinking content:", thinking_content)
print("content:", content)

Citations

Qwen3

@misc{qwen3technicalreport,
      title={Qwen3 Technical Report}, 
      author={Qwen Team},
      year={2025},
      eprint={2505.09388},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.09388}, 
}

Trimming blog post

@misc{hf_blogpost_trimming,
      title={Introduction to Trimming}, 
      author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI},
      year={2026},
      url={https://huggingface.co/blog/lbourdois/introduction-to-trimming}, 
}