Instructions to use bookbot/gpt2-indo-small-kids-stories with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bookbot/gpt2-indo-small-kids-stories with Transformers:

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

pipe = pipeline("text-generation", model="bookbot/gpt2-indo-small-kids-stories")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bookbot/gpt2-indo-small-kids-stories")
model = AutoModelForCausalLM.from_pretrained("bookbot/gpt2-indo-small-kids-stories", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bookbot/gpt2-indo-small-kids-stories with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bookbot/gpt2-indo-small-kids-stories

SGLang

How to use bookbot/gpt2-indo-small-kids-stories 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 "bookbot/gpt2-indo-small-kids-stories" \
    --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": "bookbot/gpt2-indo-small-kids-stories",
		"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 "bookbot/gpt2-indo-small-kids-stories" \
        --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": "bookbot/gpt2-indo-small-kids-stories",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use bookbot/gpt2-indo-small-kids-stories with Docker Model Runner:
```
docker model run hf.co/bookbot/gpt2-indo-small-kids-stories
```

GPT-2 Indonesian Small Kids Stories

GPT-2 Indonesian Small Kids Stories is a causal language model based on the OpenAI GPT-2 model. The model was originally the pre-trained GPT2 Small Indonesian model, which was then fine-tuned on Indonesian kids' stories from Room To Read and Let's Read.

10% of the dataset was kept for evaluation purposes. The pre-trained model was fine-tuned and achieved an evaluation loss of 3.777 and an evaluation perplexity of 43.68.

Hugging Face's Trainer class from the Transformers library was used to train the model. PyTorch was used as the backend framework during training, but the model remains compatible with other frameworks nonetheless.

Model

Model	#params	Arch.	Training/Validation data (text)
`gpt2-indo-small-kids-stories`	124M	GPT2 Small	Indonesian Kids' Stories (860 KB)

Evaluation Results

The model was fine-tuned for 10 epochs.

Epoch	Training Loss	Validation Loss
1	4.259600	4.020201
2	3.979100	3.911295
3	3.818300	3.849313
4	3.691600	3.809931
5	3.589300	3.789201
6	3.506200	3.778665
7	3.439200	3.774871
8	3.387600	3.774859
9	3.351300	3.776672
10	3.330100	3.776935

How to Use (PyTorch)

As Causal Language Model

from transformers import pipeline

pretrained_name = "bookbot/gpt2-indo-small-kids-stories"

nlp = pipeline(
    "text-generation",
    model=pretrained_name,
    tokenizer=pretrained_name
)

nlp("Archie sedang mengendarai roket ke planet Mars.")

Feature Extraction in PyTorch

from transformers import GPT2LMHeadModel, GPT2TokenizerFast

pretrained_name = "bookbot/gpt2-indo-small-kids-stories"
model = GPT2LMHeadModel.from_pretrained(pretrained_name)
tokenizer = GPT2TokenizerFast.from_pretrained(pretrained_name)

prompt = "Archie sedang mengendarai roket ke planet Mars."
encoded_input = tokenizer(prompt, return_tensors='pt')
output = model(**encoded_input)

Disclaimer

Do consider the biases which come from both the pre-trained GPT-2 model and the Indonesian Kids' Stories dataset that may be carried over into the results of this model.

Author

GPT-2 Indonesian Small Kids Stories was trained and evaluated by Wilson Wongso. All computation and development are done on Google Colaboratory using their free GPU access.

Downloads last month: 339

Safetensors

Model size

0.1B params

Tensor type

F32