Instructions to use GAI-LLM/polyglot-12.8b-mixed-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GAI-LLM/polyglot-12.8b-mixed-v3 with Transformers:

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

pipe = pipeline("text-generation", model="GAI-LLM/polyglot-12.8b-mixed-v3")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GAI-LLM/polyglot-12.8b-mixed-v3")
model = AutoModelForCausalLM.from_pretrained("GAI-LLM/polyglot-12.8b-mixed-v3")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use GAI-LLM/polyglot-12.8b-mixed-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GAI-LLM/polyglot-12.8b-mixed-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GAI-LLM/polyglot-12.8b-mixed-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GAI-LLM/polyglot-12.8b-mixed-v3

SGLang

How to use GAI-LLM/polyglot-12.8b-mixed-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 "GAI-LLM/polyglot-12.8b-mixed-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": "GAI-LLM/polyglot-12.8b-mixed-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 "GAI-LLM/polyglot-12.8b-mixed-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": "GAI-LLM/polyglot-12.8b-mixed-v3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GAI-LLM/polyglot-12.8b-mixed-v3 with Docker Model Runner:
```
docker model run hf.co/GAI-LLM/polyglot-12.8b-mixed-v3
```

The license is cc-by-nc-4.0.

GAI-LLM/polyglot-12.8b-mixed-v3

Model Details

Model Developers Donghoon Oh, Hanmin Myung, Eunyoung Kim (SK C&C G.AI Eng)

Input Models input text only.

Output Models generate text only.

Model Architecture
GAI-LLM/polyglot-12.8b-mixed-v3 is an auto-regressive language model based on the polyglot transformer architecture.

Base Model EleutherAI/polyglot-ko-12.8b

Training Dataset

We combined Open Korean Dateset using mixed-strategy.
- Kopen-platypus + kaist_cot_deepL
We use A100 GPU 80GB * 8, when training.

Model Benchmark

KO-LLM leaderboard

Follow up as Open KO-LLM LeaderBoard.

Implementation Code

### GAI-LLM/polyglot-12.8b-mixed-v3
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

repo = "GAI-LLM/polyglot-12.8b-mixed-v3"
model = AutoModelForCausalLM.from_pretrained(
        repo,
        return_dict=True,
        torch_dtype=torch.float16,
        device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(repo)

Downloads last month: 2