Instructions to use PracticeLLM/Custom-KoLLM-13B-v6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PracticeLLM/Custom-KoLLM-13B-v6 with Transformers:

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

pipe = pipeline("text-generation", model="PracticeLLM/Custom-KoLLM-13B-v6")

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

tokenizer = AutoTokenizer.from_pretrained("PracticeLLM/Custom-KoLLM-13B-v6")
model = AutoModelForCausalLM.from_pretrained("PracticeLLM/Custom-KoLLM-13B-v6", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PracticeLLM/Custom-KoLLM-13B-v6 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-v6"
# 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-v6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PracticeLLM/Custom-KoLLM-13B-v6

SGLang

How to use PracticeLLM/Custom-KoLLM-13B-v6 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-v6" \
    --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-v6",
		"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-v6" \
        --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-v6",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PracticeLLM/Custom-KoLLM-13B-v6 with Docker Model Runner:
```
docker model run hf.co/PracticeLLM/Custom-KoLLM-13B-v6
```

Custom-KoLLM-13B-v6

Commit History

Apr 15, 2025

08:14
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
c17aef3

Nov 30, 2023

04:13
Upload README.md

kyujinpy

2c3e3ff

Nov 29, 2023

20:47
Upload README.md

kyujinpy

4e3b471
16:48
Upload README.md

kyujinpy

206e69b
16:47
Upload README.md

kyujinpy

9888606
08:25
Upload 3 files

kyujinpy

02d6a3c
07:36
Delete pytorch_model-00006-of-00006.bin

kyujinpy

f17857e
07:36
Delete pytorch_model-00005-of-00006.bin

kyujinpy

0023e6a
07:36
Delete pytorch_model-00004-of-00006.bin

kyujinpy

3bdb54c
07:36
Delete pytorch_model-00003-of-00006.bin

kyujinpy

7186f74
07:35
Delete pytorch_model-00002-of-00006.bin

kyujinpy

e833ed9
07:35
Delete pytorch_model-00001-of-00006.bin

kyujinpy

9a274b7
07:35
Upload 6 files

kyujinpy

b597159
06:01
Upload tokenizer

kyujinpy

3b3a2f8
06:01
Upload LlamaForCausalLM

kyujinpy

86952d9
05:31
initial commit

kyujinpy

72355fd

Commit History

Apr 15, 2025

Adding `safetensors` variant of this model⁠

Nov 30, 2023

Upload README.md

Nov 29, 2023

Upload README.md

Upload README.md

Upload README.md

Upload 3 files

Delete pytorch_model-00006-of-00006.bin

Delete pytorch_model-00005-of-00006.bin

Delete pytorch_model-00004-of-00006.bin

Delete pytorch_model-00003-of-00006.bin

Delete pytorch_model-00002-of-00006.bin

Delete pytorch_model-00001-of-00006.bin

Upload 6 files

Upload tokenizer

Upload LlamaForCausalLM

initial commit