Instructions to use skytnt/gpt2-japanese-lyric-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use skytnt/gpt2-japanese-lyric-small with Transformers:

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

pipe = pipeline("text-generation", model="skytnt/gpt2-japanese-lyric-small")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("skytnt/gpt2-japanese-lyric-small")
model = AutoModelForCausalLM.from_pretrained("skytnt/gpt2-japanese-lyric-small")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use skytnt/gpt2-japanese-lyric-small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "skytnt/gpt2-japanese-lyric-small"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "skytnt/gpt2-japanese-lyric-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/skytnt/gpt2-japanese-lyric-small

SGLang

How to use skytnt/gpt2-japanese-lyric-small 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 "skytnt/gpt2-japanese-lyric-small" \
    --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": "skytnt/gpt2-japanese-lyric-small",
		"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 "skytnt/gpt2-japanese-lyric-small" \
        --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": "skytnt/gpt2-japanese-lyric-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use skytnt/gpt2-japanese-lyric-small with Docker Model Runner:
```
docker model run hf.co/skytnt/gpt2-japanese-lyric-small
```

Japanese GPT2 Lyric Model

Model description

The model is used to generate Japanese lyrics.

You can try it on my website https://lyric.fab.moe/

How to use

import torch
from transformers import T5Tokenizer, GPT2LMHeadModel

tokenizer = T5Tokenizer.from_pretrained("skytnt/gpt2-japanese-lyric-small")
model = GPT2LMHeadModel.from_pretrained("skytnt/gpt2-japanese-lyric-small")


def gen_lyric(prompt_text: str):
    prompt_text = "<s>" + prompt_text.replace("\n", "\\n ")
    prompt_tokens = tokenizer.tokenize(prompt_text)
    prompt_token_ids = tokenizer.convert_tokens_to_ids(prompt_tokens)
    prompt_tensor = torch.LongTensor(prompt_token_ids).to(device)
    prompt_tensor = prompt_tensor.view(1, -1)
    # model forward
    output_sequences = model.generate(
        input_ids=prompt_tensor,
        max_length=512,
        top_p=0.95,
        top_k=40,
        temperature=1.0,
        do_sample=True,
        early_stopping=True,
        bos_token_id=tokenizer.bos_token_id,
        eos_token_id=tokenizer.eos_token_id,
        pad_token_id=tokenizer.pad_token_id,
        num_return_sequences=1
    )

    # convert model outputs to readable sentence
    generated_sequence = output_sequences.tolist()[0]
    generated_tokens = tokenizer.convert_ids_to_tokens(generated_sequence)
    generated_text = tokenizer.convert_tokens_to_string(generated_tokens)
    generated_text = "\n".join([s.strip() for s in generated_text.split('\\n')]).replace(' ', '\u3000').replace('<s>', '').replace('</s>', '\n\n---end---')
    return generated_text


print(gen_lyric("桜が咲く"))

Training data

Training data contains 143,587 Japanese lyrics which are collected from uta-net by lyric_download

Downloads last month: 2,088

Safetensors

Model size

0.1B params

Tensor type

F32

skytnt
/

gpt2-japanese-lyric-small

Japanese GPT2 Lyric Model

Model description

How to use

Training data

Dataset used to train skytnt/gpt2-japanese-lyric-small