Instructions to use mariklolik/AraToken-Qwen3-1.7B-LEP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mariklolik/AraToken-Qwen3-1.7B-LEP with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="mariklolik/AraToken-Qwen3-1.7B-LEP")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mariklolik/AraToken-Qwen3-1.7B-LEP")
model = AutoModelForCausalLM.from_pretrained("mariklolik/AraToken-Qwen3-1.7B-LEP", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mariklolik/AraToken-Qwen3-1.7B-LEP with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mariklolik/AraToken-Qwen3-1.7B-LEP"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mariklolik/AraToken-Qwen3-1.7B-LEP",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mariklolik/AraToken-Qwen3-1.7B-LEP

SGLang

How to use mariklolik/AraToken-Qwen3-1.7B-LEP with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "mariklolik/AraToken-Qwen3-1.7B-LEP" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mariklolik/AraToken-Qwen3-1.7B-LEP",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "mariklolik/AraToken-Qwen3-1.7B-LEP" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mariklolik/AraToken-Qwen3-1.7B-LEP",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mariklolik/AraToken-Qwen3-1.7B-LEP with Docker Model Runner:
```
docker model run hf.co/mariklolik/AraToken-Qwen3-1.7B-LEP
```

Configuration Parsing Warning:Config file tokenizer_config.json cannot be fetched (too big)

AraToken-Qwen3-1.7B-LEP

Qwen3-1.7B-Base adapted to Arabic with LEP. The 130,890 new embedding rows were initialized with the hybrid estimate ½(compositional + analogical). The model was trained for 2,000 steps (196M tokens, batch 96 × 1,024), with the original embedding rows frozen and transformer layers 24–27 trainable.

Paper: AraToken: Optimizing Arabic Tokenization with Normalization Pipeline and Language Extension for Qwen3. Code: https://github.com/mariklolik/Aratoken.

Model	Arabic BPC ↓
Qwen3-1.7B-Base	1.3313
CPT with the original tokenizer (mariklolik/AraToken-Qwen3-1.7B-CPT)	1.2672
this model	1.2598

The difference to CPT is significant at p < 0.001 (paired bootstrap over test documents).

BPC is bits per character on the first 1,500 documents of the held-out test split of mariklolik/AraToken-FineWeb2-HQ-ar. It compares models with different vocabularies on the same characters.

from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "mariklolik/AraToken-Qwen3-1.7B-LEP"
tokenizer = AutoTokenizer.from_pretrained(repo)
model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype="bfloat16")

The tokenizer carries the AraToken normalizer: NFKC, Tatweel removal, Western digits, Latin punctuation and diacritics removal. Raw Arabic text can therefore be passed to it directly.

Citation

@article{kashirskiy2025aratoken,
  title   = {AraToken: Optimizing Arabic Tokenization with Normalization Pipeline and Language Extension for Qwen3},
  author  = {Kashirskiy, Mark and Lipinski, Artiom and Makarov, Ilya},
  journal = {arXiv preprint arXiv:2512.18399},
  year    = {2025}
}

Downloads last month: 326

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for mariklolik/AraToken-Qwen3-1.7B-LEP

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

(449)

this model

Dataset used to train mariklolik/AraToken-Qwen3-1.7B-LEP

Paper for mariklolik/AraToken-Qwen3-1.7B-LEP

AraToken: Optimizing Arabic Tokenization with Normalization Pipeline and Language Extension for Qwen3

Paper • 2512.18399 • Published Dec 20, 2025