Instructions to use PracticeLLM/Custom-KoLLM-13B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PracticeLLM/Custom-KoLLM-13B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="PracticeLLM/Custom-KoLLM-13B-v1")

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

tokenizer = AutoTokenizer.from_pretrained("PracticeLLM/Custom-KoLLM-13B-v1")
model = AutoModelForCausalLM.from_pretrained("PracticeLLM/Custom-KoLLM-13B-v1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PracticeLLM/Custom-KoLLM-13B-v1 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-v1"
# 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-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PracticeLLM/Custom-KoLLM-13B-v1

SGLang

How to use PracticeLLM/Custom-KoLLM-13B-v1 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-v1" \
    --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-v1",
		"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-v1" \
        --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-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PracticeLLM/Custom-KoLLM-13B-v1 with Docker Model Runner:
```
docker model run hf.co/PracticeLLM/Custom-KoLLM-13B-v1
```

Custom-KoLLM-13B-v1

Commit History

Oct 18, 2025

19:20
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
5267344

Nov 25, 2023

18:49
Upload README.md

kyujinpy

ece285b
18:19
Upload README.md

kyujinpy

4b87796
18:18
Upload README.md

kyujinpy

90f98ee
18:17
Upload README.md

kyujinpy

b5d0dc3
18:16
Upload README.md

kyujinpy

d164f9f
18:15
Upload README.md

kyujinpy

2f497ce
18:15
Upload README.md

kyujinpy

dd3bd52

Nov 24, 2023

19:54
Upload README.md

kyujinpy

48e5ac8

Nov 23, 2023

16:25
Upload README.md

kyujinpy

f1a9c2a
04:55
Upload README.md

kyujinpy

f2647ab
04:55
Upload README.md

kyujinpy

1119c9e
04:54
Upload README.md

kyujinpy

8bdcd79
04:54
Upload README.md

kyujinpy

a557c54
04:54
Upload README.md

kyujinpy

b2e3ed4

Nov 21, 2023

17:34
Upload tokenizer

kyujinpy

3094647
17:34
Upload LlamaForCausalLM

kyujinpy

b39c75b
17:17
initial commit

kyujinpy

b0aa9ac

Commit History

Oct 18, 2025

Adding `safetensors` variant of this model⁠

Nov 25, 2023

Upload README.md

Upload README.md

Upload README.md

Upload README.md

Upload README.md

Upload README.md

Upload README.md

Nov 24, 2023

Upload README.md

Nov 23, 2023

Upload README.md

Upload README.md

Upload README.md

Upload README.md

Upload README.md

Upload README.md

Nov 21, 2023

Upload tokenizer

Upload LlamaForCausalLM

initial commit