Instructions to use chronopt-research/vietnamese-gpt2-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chronopt-research/vietnamese-gpt2-base with Transformers:

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

pipe = pipeline("text-generation", model="chronopt-research/vietnamese-gpt2-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chronopt-research/vietnamese-gpt2-base")
model = AutoModelForCausalLM.from_pretrained("chronopt-research/vietnamese-gpt2-base")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use chronopt-research/vietnamese-gpt2-base with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/chronopt-research/vietnamese-gpt2-base

SGLang

How to use chronopt-research/vietnamese-gpt2-base 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 "chronopt-research/vietnamese-gpt2-base" \
    --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": "chronopt-research/vietnamese-gpt2-base",
		"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 "chronopt-research/vietnamese-gpt2-base" \
        --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": "chronopt-research/vietnamese-gpt2-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use chronopt-research/vietnamese-gpt2-base with Docker Model Runner:
```
docker model run hf.co/chronopt-research/vietnamese-gpt2-base
```

Vietnamese `gpt2-base`

This is a pretrained gpt2-base for Vietnamese language using casual language modeling (CLM) objective. It was introduced in this paper and first released at this page.

Model Description

GPT-2 (at first) is a transformers model pretrained on a very large corpus of English data in a self-supervised fashion. This means it was pretrained on the raw texts only, with no humans labelling them in any way (which is why it can use lots of publicly available data) with an automatic process to generate inputs and labels from those texts. More precisely, it was trained to guess the next word in sentences.

This is the base version of GPT-2, with 137M parameters.

You could've found other pretrained version from here: gpt2-medium, gpt2-large

Dataset used for pretraining

This is a combination of multiple Vietnamese dataset for pretraining CLMs such as GPT, GPT2, etc.

The dataset consists of:

You can find out the combined version here: duongttr/vi-dataset-for-pretrain

Hyperparamters & Results

We trained the model ~100k steps, with lr=1e-4, bs=2560 (single_batch_size=32 * num_core=8 * grad_cum=10), optimizer=adamw on TPU-VM-3.8 from TRC Program. The training costs around 1 day.

Model	Eval Loss	Eval Perplexity
gpt2-base	3.939	51.35
gpt2-medium	2.8676	17.5948
gpt2-large	-	-

Contacts

Feel free to contact us via: email

Downloads last month: 13

Dataset used to train chronopt-research/vietnamese-gpt2-base

Evaluation results

perplexity
self-reported

51.350

Vietnamese gpt2-base