Instructions to use Muscaria/gpt2_viet_story with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Muscaria/gpt2_viet_story with Transformers:

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

pipe = pipeline("text-generation", model="Muscaria/gpt2_viet_story")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Muscaria/gpt2_viet_story")
model = AutoModelForCausalLM.from_pretrained("Muscaria/gpt2_viet_story", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Muscaria/gpt2_viet_story with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Muscaria/gpt2_viet_story"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Muscaria/gpt2_viet_story",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Muscaria/gpt2_viet_story

SGLang

How to use Muscaria/gpt2_viet_story 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 "Muscaria/gpt2_viet_story" \
    --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": "Muscaria/gpt2_viet_story",
		"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 "Muscaria/gpt2_viet_story" \
        --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": "Muscaria/gpt2_viet_story",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Muscaria/gpt2_viet_story with Docker Model Runner:
```
docker model run hf.co/Muscaria/gpt2_viet_story
```

gpt2_viet_story

This model is a fine-tuned version of NlpHUST/gpt2-vietnamese on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.3882

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.6890	1.0	28	2.5718
2.5595	2.0	56	2.4930
2.3970	3.0	84	2.4535
2.3009	4.0	112	2.4270
2.1693	5.0	140	2.4102
2.1733	6.0	168	2.3991
2.1390	7.0	196	2.3928
2.1031	8.0	224	2.3895
2.1376	9.0	252	2.3883
2.1575	10.0	280	2.3882

Framework versions

Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.8.3
Tokenizers 0.22.2

Downloads last month: 9

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for Muscaria/gpt2_viet_story

Base model

NlpHUST/gpt2-vietnamese

Finetuned

(12)

this model