Text Generation
Transformers
Safetensors
Arabic
gpt2
arabic
egyptian
dialect
slang
translation
gpt-2
aragpt
seq2seq
causal-lm
text-generation-inference
Instructions to use AdhamAshraf/SlangGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AdhamAshraf/SlangGPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AdhamAshraf/SlangGPT")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AdhamAshraf/SlangGPT") model = AutoModelForCausalLM.from_pretrained("AdhamAshraf/SlangGPT") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use AdhamAshraf/SlangGPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AdhamAshraf/SlangGPT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AdhamAshraf/SlangGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AdhamAshraf/SlangGPT
- SGLang
How to use AdhamAshraf/SlangGPT 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 "AdhamAshraf/SlangGPT" \ --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": "AdhamAshraf/SlangGPT", "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 "AdhamAshraf/SlangGPT" \ --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": "AdhamAshraf/SlangGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AdhamAshraf/SlangGPT with Docker Model Runner:
docker model run hf.co/AdhamAshraf/SlangGPT
Update README.md
Browse files
README.md
CHANGED
|
@@ -35,7 +35,7 @@ It is part of the broader SlangGPT project — an end-to-end Arabic NLP system f
|
|
| 35 |
# 📄 Project Resources
|
| 36 |
|
| 37 |
- **Paper:**
|
| 38 |
-
https://github.com/adhamashraf7788/SlangGPT/blob/main/report/
|
| 39 |
|
| 40 |
- **Main Dataset:**
|
| 41 |
https://huggingface.co/datasets/AdhamAshraf/egyptian-2-arabic
|
|
|
|
| 35 |
# 📄 Project Resources
|
| 36 |
|
| 37 |
- **Paper:**
|
| 38 |
+
https://github.com/adhamashraf7788/SlangGPT/blob/main/report/SlangGPT report.pdf
|
| 39 |
|
| 40 |
- **Main Dataset:**
|
| 41 |
https://huggingface.co/datasets/AdhamAshraf/egyptian-2-arabic
|