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

Libraries

How to use EleutherAI/polyglot-ko-5.8b with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EleutherAI/polyglot-ko-5.8b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/EleutherAI/polyglot-ko-5.8b

SGLang

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

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

bzantium commited on Jun 7, 2023

Commit

581a4c3

1 Parent(s): 08c8b1c

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -6

README.md CHANGED Viewed

@@ -168,12 +168,13 @@ Polyglot-Ko has been trained to optimize next token prediction. Language models
 ### BibTeX entry
 If you find our work useful, please consider citing:
 ```bibtex
-@misc{polyglot-ko,
-  title = {{Polyglot-Ko: Open-Source Korean Autoregressive Language Model}},
-  author = {Ko, Hyunwoong and Yang, Kichang and Ryu, Minho and Choi, Taekyoon and Yang, Seungmu and Hyun, jiwung and Park, Sungho},
-  url = {https://www.github.com/eleutherai/polyglot},
-  month = {9},
-  year = {2022},
 }
 ```

 ### BibTeX entry
 If you find our work useful, please consider citing:
 ```bibtex
+@misc{ko2023technical,
+      title={A Technical Report for Polyglot-Ko: Open-Source Large-Scale Korean Language Models},
+      author={Hyunwoong Ko and Kichang Yang and Minho Ryu and Taekyoon Choi and Seungmu Yang and jiwung Hyun and Sungho Park},
+      year={2023},
+      eprint={2306.02254},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL}
 }
 ```