Instructions to use nayohan/polyglot-ko-5.8b-Inst-All with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nayohan/polyglot-ko-5.8b-Inst-All with Transformers:

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

pipe = pipeline("text-generation", model="nayohan/polyglot-ko-5.8b-Inst-All")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nayohan/polyglot-ko-5.8b-Inst-All")
model = AutoModelForCausalLM.from_pretrained("nayohan/polyglot-ko-5.8b-Inst-All")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nayohan/polyglot-ko-5.8b-Inst-All with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nayohan/polyglot-ko-5.8b-Inst-All"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nayohan/polyglot-ko-5.8b-Inst-All",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/nayohan/polyglot-ko-5.8b-Inst-All

SGLang

How to use nayohan/polyglot-ko-5.8b-Inst-All 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 "nayohan/polyglot-ko-5.8b-Inst-All" \
    --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": "nayohan/polyglot-ko-5.8b-Inst-All",
		"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 "nayohan/polyglot-ko-5.8b-Inst-All" \
        --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": "nayohan/polyglot-ko-5.8b-Inst-All",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use nayohan/polyglot-ko-5.8b-Inst-All with Docker Model Runner:
```
docker model run hf.co/nayohan/polyglot-ko-5.8b-Inst-All
```

This model is a instruct-tuned poylglot-ko-5.8b model, using full [Kullm, OIG, KoAlpaca] Instruction dataset. koquality_raw.json -> 410step

Training hyperparameters

learning_rate: 5e-5
train_batch_size: 2
seed: 42
distributed_type: multi-GPU (A30 24G) + CPU Offloading
num_devices: 2
gradient_accumulation_steps: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1.0

Framework versions

Transformers 4.30.2
Pytorch 2.0.1+cu117
Datasets 2.11.0
deepspeed 0.9.5

Downloads last month: 14

Model tree for nayohan/polyglot-ko-5.8b-Inst-All

Base model

EleutherAI/polyglot-ko-5.8b

Finetuned

(7)

this model

nayohan
/

polyglot-ko-5.8b-Inst-All

Training hyperparameters

Framework versions

Model tree for nayohan/polyglot-ko-5.8b-Inst-All

Dataset used to train nayohan/polyglot-ko-5.8b-Inst-All