Instructions to use mabaji/thepoet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mabaji/thepoet with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="mabaji/thepoet")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("mabaji/thepoet") model = AutoModelForMultimodalLM.from_pretrained("mabaji/thepoet") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use mabaji/thepoet with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "mabaji/thepoet" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "mabaji/thepoet", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/mabaji/thepoet
- SGLang
How to use mabaji/thepoet 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 "mabaji/thepoet" \ --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": "mabaji/thepoet", "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 "mabaji/thepoet" \ --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": "mabaji/thepoet", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use mabaji/thepoet with Docker Model Runner:
docker model run hf.co/mabaji/thepoet
Thepoet is an Arabic poem generator, pre-trained language model based on OpenAi GPT2 architechture.
Special thanks to aubmindlab for their pretrained Arabic model - Aragpt2 - large (https://huggingface.co/aubmindlab/aragpt2-large)
AraGPT2-large adafactor 1024 1280 20 36 2.98GB/792M
Trained on two huge (APCD) datasets:
512MB Arabic Poem Comprehensive Dataset from Kaggle (https://www.kaggle.com/datasets/mohamedkhaledelsafty/best-arabic-poem-comprehensive-dataset)
150MB Arabic Poem Dataset from Kaggle(https://www.kaggle.com/datasets/ahmedabelal/arabic-poetry)
Eval results
Final perplexity reached was 119.5661
BibTeX entry and citation info
@inproceedings{Mohamad El Abaji,
year={2022}
}
- Downloads last month
- 4