Instructions to use U4RASD/ar-ms-baseline with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use U4RASD/ar-ms-baseline with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-VL-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "U4RASD/ar-ms-baseline")

Transformers

How to use U4RASD/ar-ms-baseline with Transformers:

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

pipe = pipeline("text-generation", model="U4RASD/ar-ms-baseline")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("U4RASD/ar-ms-baseline", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use U4RASD/ar-ms-baseline with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "U4RASD/ar-ms-baseline"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "U4RASD/ar-ms-baseline",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/U4RASD/ar-ms-baseline

SGLang

How to use U4RASD/ar-ms-baseline 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 "U4RASD/ar-ms-baseline" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "U4RASD/ar-ms-baseline",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "U4RASD/ar-ms-baseline" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "U4RASD/ar-ms-baseline",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use U4RASD/ar-ms-baseline with Docker Model Runner:
```
docker model run hf.co/U4RASD/ar-ms-baseline
```

Model Card for ar-ms-baseline

Model Summary

This model is the baseline system for the NAKBA NLP 2026: Arabic Manuscript Understanding Shared Task (Systems Track). It fine-tunes Qwen3-VL-8B-Instruct with LoRA to transcribe Arabic manuscript line images into text.

Model Details

Description

Model type: Vision-language OCR/HTR model (LoRA-adapted)
Finetuned from model: Qwen/Qwen3-VL-8B-Instruct

Sources

Repository: https://github.com/U4RASD/ar-ms-baseline
Shared Task: https://acrps.ai/nakba-nlp-manu-understanding-2026

Training Details

Training Data

NAKBA NLP 2026 Shared Task (Subtask 2) training split from the Omar Al-Saleh memoir collection.
Dataset includes line images with gold transcriptions.

Training Procedure

Supervised fine-tuning with LoRA adapters on Qwen/Qwen3-VL-8B-Instruct.

Training Hyperparameters

Config reference: Hyperparameters are listed in configs/default.json

Evaluation

Testing Data, Factors & Metrics

Testing Data

NAKBA NLP 2026 Shared Task (Subtask 2) released test set of line images.

Metrics

CER (Character Error Rate)
WER (Word Error Rate)

Results

On released test set:

CER: 0.2297
WER: 0.4998
Hardware: NVIDIA H100 SXM

Contact

ar-ms@dohainstitute.edu.qa

Downloads last month: -

Model tree for U4RASD/ar-ms-baseline

Base model

Qwen/Qwen3-VL-8B-Instruct

Adapter

(89)

this model