Text Generation
Transformers
PyTorch
Arabic
gpt2
AraGPT2
GPT-2
MSA
Arabic Text Summarization
Arabic News Title Generation
Arabic Paraphrasing
text-generation-inference
Instructions to use malmarjeh/gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use malmarjeh/gpt2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="malmarjeh/gpt2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("malmarjeh/gpt2") model = AutoModelForCausalLM.from_pretrained("malmarjeh/gpt2") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use malmarjeh/gpt2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "malmarjeh/gpt2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "malmarjeh/gpt2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/malmarjeh/gpt2
- SGLang
How to use malmarjeh/gpt2 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 "malmarjeh/gpt2" \ --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": "malmarjeh/gpt2", "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 "malmarjeh/gpt2" \ --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": "malmarjeh/gpt2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use malmarjeh/gpt2 with Docker Model Runner:
docker model run hf.co/malmarjeh/gpt2
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ A fine-tuned AraGPT2 model on a dataset of 84,764 paragraph-summary pairs.
|
|
| 17 |
|
| 18 |
Paper: [Arabic abstractive text summarization using RNN-based and transformer-based architectures](https://www.sciencedirect.com/science/article/abs/pii/S0306457322003284).
|
| 19 |
|
| 20 |
-
Dataset: [link](https://data.mendeley.com/datasets/7kr75c9h24/1)
|
| 21 |
|
| 22 |
The model can be used as follows:
|
| 23 |
```python
|
|
|
|
| 17 |
|
| 18 |
Paper: [Arabic abstractive text summarization using RNN-based and transformer-based architectures](https://www.sciencedirect.com/science/article/abs/pii/S0306457322003284).
|
| 19 |
|
| 20 |
+
Dataset: [link](https://data.mendeley.com/datasets/7kr75c9h24/1).
|
| 21 |
|
| 22 |
The model can be used as follows:
|
| 23 |
```python
|