Instructions to use tupleblog/generate-thai-lyrics with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tupleblog/generate-thai-lyrics with Transformers:

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

pipe = pipeline("text-generation", model="tupleblog/generate-thai-lyrics")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tupleblog/generate-thai-lyrics")
model = AutoModelForCausalLM.from_pretrained("tupleblog/generate-thai-lyrics")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use tupleblog/generate-thai-lyrics with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tupleblog/generate-thai-lyrics

SGLang

How to use tupleblog/generate-thai-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 "tupleblog/generate-thai-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": "tupleblog/generate-thai-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 "tupleblog/generate-thai-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": "tupleblog/generate-thai-lyrics",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use tupleblog/generate-thai-lyrics with Docker Model Runner:
```
docker model run hf.co/tupleblog/generate-thai-lyrics
```

Generate Thai Lyrics (แต่งเพลงไทยด้วย GPT-2)

GPT-2 for Thai lyrics generation. We use GPT-2 base Thai as a pre-trained model for Siamzone lyrics

เราเทรนโมเดล GPT-2 สำหรับใช้แต่งเนื้อเพลงไทยด้วยเนื้อเพลงจากเว็บไซต์ Siamzone

Example use

from transformers import pipeline
from transformers import GPT2Model, GPT2TokenizerFast, AutoModelForCausalLM, AutoTokenizer

model_name = "tupleblog/generate-thai-lyrics"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
model.config.pad_token_id = model.config.eos_token_id


nlp = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer
)
text = "ความรัก"
nlp(text, max_length=100, top_k=40, temperature=0.8) # varying the temperature and top-k produce different output

Downloads last month: 8