Instructions to use PracticeLLM/Custom-KoLLM-13B-v5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PracticeLLM/Custom-KoLLM-13B-v5 with Transformers:

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

pipe = pipeline("text-generation", model="PracticeLLM/Custom-KoLLM-13B-v5")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PracticeLLM/Custom-KoLLM-13B-v5")
model = AutoModelForCausalLM.from_pretrained("PracticeLLM/Custom-KoLLM-13B-v5", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PracticeLLM/Custom-KoLLM-13B-v5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PracticeLLM/Custom-KoLLM-13B-v5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PracticeLLM/Custom-KoLLM-13B-v5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PracticeLLM/Custom-KoLLM-13B-v5

SGLang

How to use PracticeLLM/Custom-KoLLM-13B-v5 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 "PracticeLLM/Custom-KoLLM-13B-v5" \
    --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": "PracticeLLM/Custom-KoLLM-13B-v5",
		"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 "PracticeLLM/Custom-KoLLM-13B-v5" \
        --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": "PracticeLLM/Custom-KoLLM-13B-v5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PracticeLLM/Custom-KoLLM-13B-v5 with Docker Model Runner:
```
docker model run hf.co/PracticeLLM/Custom-KoLLM-13B-v5
```

Custom-KoLLM-13B-v5

Commit History

Mar 19, 2025

23:06
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
99eb22a

Nov 29, 2023

16:46
Upload README.md

kyujinpy

25fb8d0
05:24
Upload README.md

kyujinpy

c1190fb

Nov 28, 2023

18:56
Upload README.md

kyujinpy

5fe1d01
18:49
Upload 3 files

kyujinpy

6ea8d6f
18:33
Upload 6 files

kyujinpy

2fecd93
18:32
initial commit

kyujinpy

513b761

Commit History

Mar 19, 2025

Adding `safetensors` variant of this model⁠

Nov 29, 2023

Upload README.md

Upload README.md

Nov 28, 2023

Upload README.md

Upload 3 files

Upload 6 files

initial commit