Instructions to use minhtoan/gpt3-small-vietnamese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use minhtoan/gpt3-small-vietnamese with Transformers:

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

pipe = pipeline("text-generation", model="minhtoan/gpt3-small-vietnamese")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("minhtoan/gpt3-small-vietnamese")
model = AutoModelForCausalLM.from_pretrained("minhtoan/gpt3-small-vietnamese")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use minhtoan/gpt3-small-vietnamese with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "minhtoan/gpt3-small-vietnamese"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "minhtoan/gpt3-small-vietnamese",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/minhtoan/gpt3-small-vietnamese

SGLang

How to use minhtoan/gpt3-small-vietnamese 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 "minhtoan/gpt3-small-vietnamese" \
    --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": "minhtoan/gpt3-small-vietnamese",
		"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 "minhtoan/gpt3-small-vietnamese" \
        --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": "minhtoan/gpt3-small-vietnamese",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use minhtoan/gpt3-small-vietnamese with Docker Model Runner:
```
docker model run hf.co/minhtoan/gpt3-small-vietnamese
```

GPT-3 small

Pretrained GPT Neo (GPT-3 small) , it's architecture intentionally resembles that of GPT-3, model was trained on Vietnamese dataset for text generation

How to use the model

from transformers import GPT2Tokenizer, GPTNeoForCausalLM

tokenizer = GPT2Tokenizer.from_pretrained('minhtoan/gpt3-small-vietnamese')
model = GPTNeoForCausalLM.from_pretrained('minhtoan/gpt3-small-vietnamese')

text = "Hoa quả và rau thường rẻ hơn khi vào mùa"
input_ids = tokenizer.encode(text, return_tensors='pt')
max_length = 100

sample_outputs = model.generate(input_ids, do_sample=True, max_length=max_length)

for i, sample_output in enumerate(sample_outputs):
    print(">> Generated text {}\n\n{}".format(i+1, tokenizer.decode(sample_output.tolist())))
    print('\n---')

Author

Phan Minh Toan

Downloads last month: 20