Instructions to use snoop2head/KoGPT-Joong-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use snoop2head/KoGPT-Joong-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="snoop2head/KoGPT-Joong-2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("snoop2head/KoGPT-Joong-2") model = AutoModelForCausalLM.from_pretrained("snoop2head/KoGPT-Joong-2") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use snoop2head/KoGPT-Joong-2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "snoop2head/KoGPT-Joong-2" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "snoop2head/KoGPT-Joong-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/snoop2head/KoGPT-Joong-2
- SGLang
How to use snoop2head/KoGPT-Joong-2 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 "snoop2head/KoGPT-Joong-2" \ --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": "snoop2head/KoGPT-Joong-2", "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 "snoop2head/KoGPT-Joong-2" \ --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": "snoop2head/KoGPT-Joong-2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use snoop2head/KoGPT-Joong-2 with Docker Model Runner:
docker model run hf.co/snoop2head/KoGPT-Joong-2
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
KoGPT-Joong-2
KoGPT-Joong-2's Acrostic Poem Generation Examples (Nνμ μμ)
[μ°μΈλ(1)]
μ°λ―Όμ΄λΌλ κ²μ μλ μ κ²κ³Ό κ°λ€
μΈκΈ°μ μ
μ°μΌμλ..
λκ°λ νΉλ
ν κ²μ΄λ€ μ°κΈ°μ λμ μμ²λ€
[μ°μΈλ(2)]
μ°μ½ν λ§μμΌλ‘ κ°ν μ²νμ§ λ§κ³ κ°ν λ§μμ λ¨Ήμ
μΈ λ§λ λ§λ³΄λ€ νλ§λ λ§μ΄ λ μ§μ μ± μμ΄ λ³΄μΈλ€.
λμ νμ§ λ§λΌ.
[μνν]
μκ·Έλ§νκ²
νμμ κ°μ 건λκ³
νκ²½μ λ무λ₯Ό λμ΄κ°λ€
KoGPT-Joong-2's Phrase Generation Examples
[λλ λμ]
- λλ λμ κ±°μ§λ§. λλ λμ μ°Έλ§. λλ₯Ό μμλ€λ λμ λλ₯Ό μμλ€λ λμ μ°¨μ΄.
- λλ λμ μ·μλ½μ΄κ³ λ¨Έλ¦Ώκ²°μ΄κ³ κΏκ²°μ΄κ³ λλ₯Ό ν€μ§λ μ¬μ μλ νμμ΄μλ€
[κ·Έλ μ λ΄ κΏμ]
- κ·Έλ μ λ΄ κΏμ λμ€μ§ μλ κ±ΈκΉμ, λ΄ κΏ μμμλ κ·Έλ μ¬λΌμ§λ©΄ μ΄μ©λμ
- κ·Έλ μ λ΄ κΏμ λΆμμ°©νλκ°.
Dataset finetuned on
Dependencies Installation
pip install -r requirements.txt
References
- Downloads last month
- 7