Instructions to use iko-01/ARABIC_poetry2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use iko-01/ARABIC_poetry2 with Transformers:

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

pipe = pipeline("text-generation", model="iko-01/ARABIC_poetry2")

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

tokenizer = AutoTokenizer.from_pretrained("iko-01/ARABIC_poetry2")
model = AutoModelForCausalLM.from_pretrained("iko-01/ARABIC_poetry2", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use iko-01/ARABIC_poetry2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "iko-01/ARABIC_poetry2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "iko-01/ARABIC_poetry2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/iko-01/ARABIC_poetry2

SGLang

How to use iko-01/ARABIC_poetry2 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 "iko-01/ARABIC_poetry2" \
    --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": "iko-01/ARABIC_poetry2",
		"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 "iko-01/ARABIC_poetry2" \
        --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": "iko-01/ARABIC_poetry2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use iko-01/ARABIC_poetry2 with Docker Model Runner:
```
docker model run hf.co/iko-01/ARABIC_poetry2
```

from transformers import pipeline

gen = pipeline("text-generation", model="iko-01/ARABIC_poetry2", tokenizer="iko-01/ARABIC_poetry2", device=0 if torch.cuda.is_available() else -1)

# ضع هنا أمثلة الاختبار (كلمات مفردة أو جمل قصيرة) — يمكنك تعديلها أو إضافة المزيد
prompts = [
    "يا لَطيفَ",
    "قَدْ سمعْتُ",
    "حينَ اشتدَّ",
    "يا ذاكرةَ",
    "قَلبي",
    "في الليلِ",
]

results = []
for p in prompts:
    out = gen(p,
              max_new_tokens=150,
              do_sample=True,
              top_k=50,
              top_p=0.95,
              temperature=0.8,
              num_return_sequences=1)
    text = out[0]["generated_text"]
    # نريد فقط الجزء الجديد بعد الـ prompt (أو يمكن إخراج السطر كله)
    # هنا نحتفظ بالنص الكامل لمرونة العرض
    results.append({"prompt": p, "output": text})

# عرض سريع
for r in results:
    print("PROMPT:", r["prompt"])
    print("OUTPUT:", r["output"])
    print("-"*40)

Downloads last month: 12

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for iko-01/ARABIC_poetry2

Base model

aubmindlab/aragpt2-base

Finetuned

iko-01/ARABIC_poetry

Finetuned

(1)

this model