Instructions to use jonomon/gpt3-kor-small_based_on_gpt2_core_ml with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jonomon/gpt3-kor-small_based_on_gpt2_core_ml with Transformers:

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

pipe = pipeline("text-generation", model="jonomon/gpt3-kor-small_based_on_gpt2_core_ml")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("jonomon/gpt3-kor-small_based_on_gpt2_core_ml")
model = AutoModelForMultimodalLM.from_pretrained("jonomon/gpt3-kor-small_based_on_gpt2_core_ml")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jonomon/gpt3-kor-small_based_on_gpt2_core_ml with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jonomon/gpt3-kor-small_based_on_gpt2_core_ml"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jonomon/gpt3-kor-small_based_on_gpt2_core_ml",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jonomon/gpt3-kor-small_based_on_gpt2_core_ml

SGLang

How to use jonomon/gpt3-kor-small_based_on_gpt2_core_ml 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 "jonomon/gpt3-kor-small_based_on_gpt2_core_ml" \
    --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": "jonomon/gpt3-kor-small_based_on_gpt2_core_ml",
		"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 "jonomon/gpt3-kor-small_based_on_gpt2_core_ml" \
        --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": "jonomon/gpt3-kor-small_based_on_gpt2_core_ml",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jonomon/gpt3-kor-small_based_on_gpt2_core_ml with Docker Model Runner:
```
docker model run hf.co/jonomon/gpt3-kor-small_based_on_gpt2_core_ml
```

Bert base model for Korean

70GB Korean text dataset and 42000 lower-cased subwords are used
Check the model performance and other language models for Korean in github

from transformers import BertTokenizerFast, GPT2LMHeadModel
tokenizer_gpt3 = BertTokenizerFast.from_pretrained("kykim/gpt3-kor-small_based_on_gpt2")
input_ids = tokenizer_gpt3.encode("text to tokenize")[1:]  # remove cls token
        
model_gpt3 = GPT2LMHeadModel.from_pretrained("kykim/gpt3-kor-small_based_on_gpt2")

Downloads last month: 5