Instructions to use kyujinpy/Ko-PlatYi-6B-O with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kyujinpy/Ko-PlatYi-6B-O with Transformers:

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

pipe = pipeline("text-generation", model="kyujinpy/Ko-PlatYi-6B-O")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kyujinpy/Ko-PlatYi-6B-O")
model = AutoModelForCausalLM.from_pretrained("kyujinpy/Ko-PlatYi-6B-O")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kyujinpy/Ko-PlatYi-6B-O with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kyujinpy/Ko-PlatYi-6B-O"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kyujinpy/Ko-PlatYi-6B-O",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kyujinpy/Ko-PlatYi-6B-O

SGLang

How to use kyujinpy/Ko-PlatYi-6B-O 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 "kyujinpy/Ko-PlatYi-6B-O" \
    --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": "kyujinpy/Ko-PlatYi-6B-O",
		"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 "kyujinpy/Ko-PlatYi-6B-O" \
        --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": "kyujinpy/Ko-PlatYi-6B-O",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kyujinpy/Ko-PlatYi-6B-O with Docker Model Runner:
```
docker model run hf.co/kyujinpy/Ko-PlatYi-6B-O
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Ko-PlatYi-6B-O

Model Details

Model Developers Kyujin Han (kyujinpy)

Input Models input text only.

Output Models generate text only.

Model Architecture
Ko-PlatYi-6B-O is an auto-regressive language model based on the Yi-34B transformer architecture.

Blog Link
Blog: [Coming soon...]
Github: [Coming soon...]

Base Model
beomi/Yi-Ko-6B

Training Dataset
kyujinpy/KOR-OpenOrca-Platypus-v3.

Model Benchmark

Open leaderboard

Follow up as link.

Model	Average	ARC	HellaSwag	MMLU	TruthfulQA	CommonGen-V2
Ko-PlatYi-6B-O	49.00	43.52	53.59	47.47	41.01	59.39
Ko-PlatYi-6B-kiwi	48.75	41.98	53.61	46.10	38.30	63.75
Ko-PlatYi-6B-gu	48.76	42.75	54.00	44.66	41.22	61.16
Ko-PlatYi-6B	49.97	43.00	53.55	46.50	40.31	66.47
Yi-Ko-6B	48.79	41.04	53.39	46.28	41.64	61.63

AI-Harness Evaluation

AI-Harness evaluation; link

Model	BoolQ	Copa	HellaSwag	Sentineg
	Zero-shot
Ko-PlatYi-6B-O	0.3343	0.7687	0.4833	0.5794
Ko-PlatYi-6B-kiwi	0.3343	0.7665	0.4746	0.6248
Ko-PlatYi-6B-gu	0.7077	0.7696	0.4797	0.3979
Ko-PlatYi-6B	0.3343	0.7684	0.4917	0.5226
Yi-Ko-6B	0.7070	0.7696	0.5009	0.4044

Implementation Code

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

repo = "kyujinpy/Ko-PlatYi-6B-O"
OpenOrca = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)

Downloads last month: 10

Model tree for kyujinpy/Ko-PlatYi-6B-O

Quantizations

1 model

kyujinpy
/

Ko-PlatYi-6B-O