Instructions to use PracticeLLM/Custom-KoLLM-13B-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PracticeLLM/Custom-KoLLM-13B-v3 with Transformers:

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

pipe = pipeline("text-generation", model="PracticeLLM/Custom-KoLLM-13B-v3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PracticeLLM/Custom-KoLLM-13B-v3")
model = AutoModelForCausalLM.from_pretrained("PracticeLLM/Custom-KoLLM-13B-v3")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PracticeLLM/Custom-KoLLM-13B-v3 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-v3"
# 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-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PracticeLLM/Custom-KoLLM-13B-v3

SGLang

How to use PracticeLLM/Custom-KoLLM-13B-v3 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-v3" \
    --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-v3",
		"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-v3" \
        --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-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PracticeLLM/Custom-KoLLM-13B-v3 with Docker Model Runner:
```
docker model run hf.co/PracticeLLM/Custom-KoLLM-13B-v3
```

Custom-KoLLM-13B-v3 / README.md

kyujinpy

Upload README.md

b740421 over 2 years ago

preview code

raw

history blame contribute delete

2.33 kB

metadata

language:
  - ko
datasets:
  - kyujinpy/Ko-various-dataset
library_name: transformers
pipeline_tag: text-generation
license: cc-by-nc-sa-4.0

⭐My custom LLM 13B⭐

Model Details

Model Developers

Kyujin Han (kyujinpy)

Model Architecture

My custom LLM 13B is an auto-regressive language model based on the LLaMA2 transformer architecture.

Base Model

beomi/llama-2-koen-13b

Training Dataset

kyujinpy/Ko-various-dataset.

Model comparisons

Ko-LLM leaderboard(11/27; link)

Model	Average	Ko-ARC	Ko-HellaSwag	Ko-MMLU	Ko-TruthfulQA	Ko-CommonGen V2
⭐My custom LLM 13B-v1⭐	50.19	45.99	56.93	41.78	41.66	64.58
⭐My custom LLM 13B-v2⭐	48.28	45.73	56.97	38.77	38.75	61.16
⭐My custom LLM 13B-v3⭐	46.40	44.71	56.89	40.86	44.22	45.34

Model comparisons2

AI-Harness evaluation; link

Model	Copa	Copa	HellaSwag	HellaSwag	BoolQ	BoolQ	Sentineg	Sentineg
	0-shot	5-shot	0-shot	5-shot	0-shot	5-shot	0-shot	5-shot
⭐My custom LLM 13B-v1⭐	0.7987	0.8269	0.4994	0.5660	0.3343	0.5060	0.6984	0.9723
⭐My custom LLM 13B-v2⭐	0.7938	0.8209	0.4978	0.4893	0.3343	0.5614	0.6283	0.9773
⭐My custom LLM 13B-v3⭐	0.8107	0.8359	0.5176	0.5182	0.6702	0.7851	0.5241	0.9698
beomi/llama-2-koen-13b	0.7768	0.8128	0.4999	0.5127	0.3988	0.7038	0.5870	0.9748

Implementation Code

### KO-Platypus
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "PracticeLLM/Custom-KoLLM-13B-v3"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)