Instructions to use Congi-libya/BayanSimplify-v0.2-Fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Congi-libya/BayanSimplify-v0.2-Fast with Transformers:

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

pipe = pipeline("text-generation", model="Congi-libya/BayanSimplify-v0.2-Fast")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("Congi-libya/BayanSimplify-v0.2-Fast")
model = AutoModelForSeq2SeqLM.from_pretrained("Congi-libya/BayanSimplify-v0.2-Fast", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Congi-libya/BayanSimplify-v0.2-Fast with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Congi-libya/BayanSimplify-v0.2-Fast"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Congi-libya/BayanSimplify-v0.2-Fast",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Congi-libya/BayanSimplify-v0.2-Fast

SGLang

How to use Congi-libya/BayanSimplify-v0.2-Fast 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 "Congi-libya/BayanSimplify-v0.2-Fast" \
    --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": "Congi-libya/BayanSimplify-v0.2-Fast",
		"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 "Congi-libya/BayanSimplify-v0.2-Fast" \
        --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": "Congi-libya/BayanSimplify-v0.2-Fast",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Congi-libya/BayanSimplify-v0.2-Fast with Docker Model Runner:
```
docker model run hf.co/Congi-libya/BayanSimplify-v0.2-Fast
```

BayanSimplify-v0.2-Fast / README.md

marwanelamami

Card: official pipeline tag (text-generation)

5b8a165 verified 14 days ago

preview code

Raw History Blame Contribute Delete

3.44 kB

	---
	language:
	- ar
	license: cc-by-nc-4.0
	base_model: moussaKam/AraBART
	pipeline_tag: text-generation
	library_name: transformers
	tags:
	- text-simplification
	- arabic
	- dyslexia
	- bayan
	- arabart
	- bart
	---

	# BayanSimplify-v0.2-Fast

	Model 2 of the Bayan project, compact: AraBART on the same 22,733-pair mix, the app's fast default.

	## What it does

	The same data and tags as BayanSimplify-v0.2 on AraBART (139M parameters, a third of the size), so it fits a 250 MB
	download as an int8 bundle (222 MB) and shows the first word on a mid-range phone in 82–172 ms.

	Input: `بسط: ` (without the shadda, which AraBART's tokenizer cannot read), then an optional tag such as `[S2] `,
	then the text.

	BayanBench v2.0, test, core items:

	\| Setting \| Meaning kept \| Longest clause, words cut \|
	\|---\|---\|---\|
	\| `[S2]`, float \| 40.1% \| 6.7 \|
	\| no tag, float \| 51.4% \| 4.9 \|
	\| no tag, int8 in the app \| 50.5% \| 4.8 \|

	Fast, but it keeps the meaning less often than the AraT5v2 models; the app offers BayanSimplify-v0.3 as its large
	model.

	## Use

	```python
	from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

	repo = "Congi-libya/BayanSimplify-v0.2-Fast"
	tok = AutoTokenizer.from_pretrained(repo)
	model = AutoModelForSeq2SeqLM.from_pretrained(repo)

	text = "وقد أدى التوسع العمراني السريع الذي شهدته المدينة خلال العقدين الماضيين إلى ازدحام مروري خانق في ساعات الذروة."
	x = tok("بسط: " + text, return_tensors="pt", max_length=256, truncation=True)
	y = model.generate(**x, num_beams=1, no_repeat_ngram_size=3, max_length=256)
	print(tok.decode(y[0], skip_special_tokens=True))
	```

	## The BayanSimplify family

	\| Model \| What it is \| Base model \| Training data \| In the Bayan app \|
	\|---\|---\|---\|---\|---\|
	\| [BayanSimplify-v0.1](https://huggingface.co/Congi-libya/BayanSimplify-v0.1) \| Model 1 \| AraT5v2-base-1024 \| SAMER, level 5 → 3 \| not shipped \|
	\| [BayanSimplify-v0.2](https://huggingface.co/Congi-libya/BayanSimplify-v0.2) \| Model 2 \| AraT5v2-base-1024 \| 22,733-pair mix (SAMER, Baseet, DAASI) with strength tags \| "Earlier large model" \|
	\| [BayanSimplify-v0.2-Fast](https://huggingface.co/Congi-libya/BayanSimplify-v0.2-Fast) \| Model 2, compact \| AraBART \| the same mix \| "Fast model", the default download \|
	\| [BayanSimplify-v0.3](https://huggingface.co/Congi-libya/BayanSimplify-v0.3) \| Model 3, our best \| AraT5v2-base-1024 \| [Bayan corpus v1](https://huggingface.co/datasets/Congi-libya/bayan-simplification-corpus), 14,975 rows \| "Large model", four beams \|
	\| [BayanSimplify-ONNX](https://huggingface.co/Congi-libya/BayanSimplify-ONNX) \| The int8 bundles the app downloads \| \| \| v0.2-Fast, v0.2, v0.3 \|

	## Licence and data

	CC BY-NC 4.0 (non-commercial), in line with the training data's terms. SAMER is used under the CAMeL Lab's permission to
	fine-tune and share weights for non-commercial use; its text is not redistributed here.

	## About Bayan

	Bayan (بيان) simplifies Arabic text for readers with dyslexia, entirely on an Android phone: select text in any app,
	choose «تبسيط» (Simplify), and a simpler version appears over the page. Built by Team Cogni for the Samsung Innovation
	Campus AI capstone, 2026. Every number on this card comes from the team's final report and BayanBench v2.0, the
	benchmark built for the task (meaning scored by Gemma 4 31B, checked against human raters, AUC 0.85).