Instructions to use Suchinthana/sinhala-gpt-neo-cc100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Suchinthana/sinhala-gpt-neo-cc100 with Transformers:

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

pipe = pipeline("text-generation", model="Suchinthana/sinhala-gpt-neo-cc100")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Suchinthana/sinhala-gpt-neo-cc100")
model = AutoModelForCausalLM.from_pretrained("Suchinthana/sinhala-gpt-neo-cc100")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Suchinthana/sinhala-gpt-neo-cc100 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-cc100"
# 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-cc100",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Suchinthana/sinhala-gpt-neo-cc100

SGLang

How to use Suchinthana/sinhala-gpt-neo-cc100 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-cc100" \
    --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-cc100",
		"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-cc100" \
        --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-cc100",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Suchinthana/sinhala-gpt-neo-cc100 with Docker Model Runner:
```
docker model run hf.co/Suchinthana/sinhala-gpt-neo-cc100
```

Fine tuned GPT Neo 125M with CC100 Dataset

This model is fine tuned with more than 170,000 lines from CC100 Sinhala data set for Sinhala text generation.

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-cc100')
>>> generator("අද මට ඊළඟ ", do_sample=True, max_length=500)

Downloads last month: 5

Safetensors

Model size

0.2B params

Tensor type

F32