Instructions to use heegyu/kogpt-neox-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use heegyu/kogpt-neox-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="heegyu/kogpt-neox-tiny")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("heegyu/kogpt-neox-tiny") model = AutoModelForCausalLM.from_pretrained("heegyu/kogpt-neox-tiny") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use heegyu/kogpt-neox-tiny with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "heegyu/kogpt-neox-tiny" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "heegyu/kogpt-neox-tiny", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/heegyu/kogpt-neox-tiny
- SGLang
How to use heegyu/kogpt-neox-tiny 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 "heegyu/kogpt-neox-tiny" \ --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": "heegyu/kogpt-neox-tiny", "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 "heegyu/kogpt-neox-tiny" \ --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": "heegyu/kogpt-neox-tiny", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use heegyu/kogpt-neox-tiny with Docker Model Runner:
docker model run hf.co/heegyu/kogpt-neox-tiny
Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ PoC를 위해 학습한 작은 GPT 모델
|
|
| 22 |
## 학습 환경 및 하이퍼파라미터
|
| 23 |
- NVIDIA Tesla T4(16GB VRAM)
|
| 24 |
- fp 16, deepspeed stage2
|
| 25 |
-
- 350000 steps
|
| 26 |
- batch size 32
|
| 27 |
- learning rate 5e-5, linear scheduler
|
| 28 |
- 최종 train loss: 3.684
|
|
|
|
| 22 |
## 학습 환경 및 하이퍼파라미터
|
| 23 |
- NVIDIA Tesla T4(16GB VRAM)
|
| 24 |
- fp 16, deepspeed stage2
|
| 25 |
+
- 350000 steps, 2일 17시간 소요
|
| 26 |
- batch size 32
|
| 27 |
- learning rate 5e-5, linear scheduler
|
| 28 |
- 최종 train loss: 3.684
|