Instructions to use VietAI/gpt-j-6B-vietnamese-news with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VietAI/gpt-j-6B-vietnamese-news with Transformers:

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

pipe = pipeline("text-generation", model="VietAI/gpt-j-6B-vietnamese-news")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VietAI/gpt-j-6B-vietnamese-news")
model = AutoModelForCausalLM.from_pretrained("VietAI/gpt-j-6B-vietnamese-news")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use VietAI/gpt-j-6B-vietnamese-news with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VietAI/gpt-j-6B-vietnamese-news"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VietAI/gpt-j-6B-vietnamese-news",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/VietAI/gpt-j-6B-vietnamese-news

SGLang

How to use VietAI/gpt-j-6B-vietnamese-news 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 "VietAI/gpt-j-6B-vietnamese-news" \
    --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": "VietAI/gpt-j-6B-vietnamese-news",
		"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 "VietAI/gpt-j-6B-vietnamese-news" \
        --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": "VietAI/gpt-j-6B-vietnamese-news",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use VietAI/gpt-j-6B-vietnamese-news with Docker Model Runner:
```
docker model run hf.co/VietAI/gpt-j-6B-vietnamese-news
```

GPT-J 6B on Vietnamese News

Details will be available soon.

For more information, please contact anhduongng.1001@gmail.com (Dương) / imthanhlv@gmail.com (Thành) / nguyenvulebinh@gmail.com (Bình).

How to use

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("VietAI/gpt-j-6B-vietnamese-news")
model = AutoModelForCausalLM.from_pretrained("VietAI/gpt-j-6B-vietnamese-news", low_cpu_mem_usage=True)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu") 
model.to(device)

prompt = "Tiềm năng của trí tuệ nhân tạo" # your input sentence
input_ids = tokenizer(prompt, return_tensors="pt")['input_ids'].to(device)

gen_tokens = model.generate(
        input_ids,
        max_length=max_length,
        do_sample=True,
        temperature=0.9,
        top_k=20,
    )

gen_text = tokenizer.batch_decode(gen_tokens)[0]
print(gen_text)

Downloads last month: 196