Instructions to use Suchinthana/sinhala-gpt-neo-siwiki with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Suchinthana/sinhala-gpt-neo-siwiki with Transformers:

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

pipe = pipeline("text-generation", model="Suchinthana/sinhala-gpt-neo-siwiki")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Suchinthana/sinhala-gpt-neo-siwiki")
model = AutoModelForCausalLM.from_pretrained("Suchinthana/sinhala-gpt-neo-siwiki")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Suchinthana/sinhala-gpt-neo-siwiki with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Suchinthana/sinhala-gpt-neo-siwiki

SGLang

How to use Suchinthana/sinhala-gpt-neo-siwiki 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 "Suchinthana/sinhala-gpt-neo-siwiki" \
    --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": "Suchinthana/sinhala-gpt-neo-siwiki",
		"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 "Suchinthana/sinhala-gpt-neo-siwiki" \
        --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": "Suchinthana/sinhala-gpt-neo-siwiki",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Suchinthana/sinhala-gpt-neo-siwiki with Docker Model Runner:
```
docker model run hf.co/Suchinthana/sinhala-gpt-neo-siwiki
```

Fine tuned GPT Neo 125M with Sinhala Wikipedia Dataset

This model is fine tuned with acrticles from Sinhala Wikipedia Dataset for Sinhala text generation. Only the articles with word count in between 60 and 500 were used here.

How to use

You can use this model directly with a pipeline for text generation. This example generates a different sequence each time it's run:

>>> from transformers import pipeline
>>> generator = pipeline('text-generation', model='Suchinthana/sinhala-gpt-neo-siwiki')
>>> generator("නිර්මාණය කිරීම සඳහා ", do_sample=True, max_length=500)

Downloads last month: 4

Safetensors

Model size

0.2B params

Tensor type

F32

Suchinthana
/

sinhala-gpt-neo-siwiki

Fine tuned GPT Neo 125M with Sinhala Wikipedia Dataset

How to use

Dataset used to train Suchinthana/sinhala-gpt-neo-siwiki