Instructions to use PracticeLLM/Custom-KoLLM-13B-v8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PracticeLLM/Custom-KoLLM-13B-v8 with Transformers:

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

pipe = pipeline("text-generation", model="PracticeLLM/Custom-KoLLM-13B-v8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PracticeLLM/Custom-KoLLM-13B-v8")
model = AutoModelForCausalLM.from_pretrained("PracticeLLM/Custom-KoLLM-13B-v8")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PracticeLLM/Custom-KoLLM-13B-v8 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-v8"
# 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-v8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PracticeLLM/Custom-KoLLM-13B-v8

SGLang

How to use PracticeLLM/Custom-KoLLM-13B-v8 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-v8" \
    --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-v8",
		"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-v8" \
        --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-v8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PracticeLLM/Custom-KoLLM-13B-v8 with Docker Model Runner:
```
docker model run hf.co/PracticeLLM/Custom-KoLLM-13B-v8
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

⭐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/OpenOrca-ko-v3.

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-v4⭐	49.89	45.05	57.06	41.83	42.93	62.57
⭐My custom LLM 13B-v8⭐	49.84	45.65	56.98	41.37	41.42	59.50

Implementation Code

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

repo = "PracticeLLM/Custom-KoLLM-13B-v8"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)

Hyperparameters

QLoRA
lora_target_modules '[gate_proj, down_proj, up_proj]'
lora_r 64

Downloads last month: 7

Safetensors

Model size

13B params

Tensor type

F16

Model tree for PracticeLLM/Custom-KoLLM-13B-v8

Quantizations

4 models

PracticeLLM
/

Custom-KoLLM-13B-v8