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

Libraries

How to use Ransaka/sinhala-gpt-lyrics with Transformers:

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

pipe = pipeline("text-generation", model="Ransaka/sinhala-gpt-lyrics")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ransaka/sinhala-gpt-lyrics")
model = AutoModelForCausalLM.from_pretrained("Ransaka/sinhala-gpt-lyrics")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ransaka/sinhala-gpt-lyrics with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Ransaka/sinhala-gpt-lyrics

SGLang

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

Docker Model Runner
How to use Ransaka/sinhala-gpt-lyrics with Docker Model Runner:
```
docker model run hf.co/Ransaka/sinhala-gpt-lyrics
```

sinhala-gpt-lyrics

This particular model has undergone fine-tuning based on the gpt2 architecture, utilizing a dataset of around 500k Sinhala lyrics from various sources. This Model is not sophisticated at all. Created while following one of fine-tuning docs.

Usage Details

from transformers import AutoTokenizer, AutoModelForCausalLM,pipeline

tokenizer = AutoTokenizer.from_pretrained("Ransaka/sinhala-gpt-lyrics")
model = AutoModelForCausalLM.from_pretrained("Ransaka/sinhala-gpt-lyrics")
generator = pipeline('text-generation',model=model, tokenizer=tokenizer)
generator("දුර") #දුර ඈත පාසැල් වියේ.

or using git

git lfs install
git clone https://huggingface.co/Ransaka/sinhala-gpt-lyrics

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.3015	1.0	15323	2.3498
1.8582	2.0	30646	1.9921
1.5491	3.0	45969	1.9376

Framework versions

Transformers 4.26.1
Pytorch 1.13.0
Datasets 2.1.0
Tokenizers 0.13.2

Downloads last month: 3