Instructions to use monsoon-nlp/sanaa-dialect with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use monsoon-nlp/sanaa-dialect with Transformers:

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

pipe = pipeline("text-generation", model="monsoon-nlp/sanaa-dialect")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("monsoon-nlp/sanaa-dialect")
model = AutoModelForCausalLM.from_pretrained("monsoon-nlp/sanaa-dialect")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use monsoon-nlp/sanaa-dialect with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/monsoon-nlp/sanaa-dialect

SGLang

How to use monsoon-nlp/sanaa-dialect 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 "monsoon-nlp/sanaa-dialect" \
    --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": "monsoon-nlp/sanaa-dialect",
		"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 "monsoon-nlp/sanaa-dialect" \
        --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": "monsoon-nlp/sanaa-dialect",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use monsoon-nlp/sanaa-dialect with Docker Model Runner:
```
docker model run hf.co/monsoon-nlp/sanaa-dialect
```

Sanaa-Dialect

Finetuned Arabic GPT-2 demo

This is a small GPT-2 model, originally trained on Arabic Wikipedia circa September 2020 , finetuned on dialect datasets from Qatar University, University of British Columbia / NLP, and Johns Hopkins University / LREC

You can use special tokens to prompt five dialects: [EGYPTIAN], [GULF], [LEVANTINE], [MAGHREBI], and [MSA]

from simpletransformers.language_generation import LanguageGenerationModel
model = LanguageGenerationModel("gpt2", "monsoon-nlp/sanaa-dialect")
model.generate('[GULF]' + "مدينتي هي", { 'max_length': 100 })

There is NO content filtering in the current version; do not use for public-facing text generation!

Training and Finetuning details

Original model and training: https://huggingface.co/monsoon-nlp/sanaa

I inserted new tokens into the tokenizer, finetuned the model on the dialect samples, and exported the new model.

Notebook: https://colab.research.google.com/drive/1fXFH7g4nfbxBo42icI4ZMy-0TAGAxc2i

شكرا لتجربة هذا! ارجو التواصل معي مع الاسئلة

Downloads last month: 3

Safetensors

Model size

0.1B params

Tensor type

F32