Instructions to use openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf with Transformers:

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

pipe = pipeline("text-generation", model="openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf")
model = AutoModelForCausalLM.from_pretrained("openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf

SGLang

How to use openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf 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 "openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf" \
    --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": "openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf",
		"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 "openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf" \
        --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": "openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf with Docker Model Runner:
```
docker model run hf.co/openthaigpt/openthaigpt-0.1.0-beta-ckpt-hf
```

openthaigpt-0.1.0-beta-ckpt-hf / README.md

kobkrit

Update README.md

f29dd21 about 3 years ago

preview code

Raw

History Blame Contribute Delete

2.94 kB

	---
	license: apache-2.0
	datasets:
	- kobkrit/rd-taxqa
	- iapp_wiki_qa_squad
	- Thaweewat/alpaca-cleaned-52k-th
	- Thaweewat/instruction-wild-52k-th
	- Thaweewat/databricks-dolly-15k-th
	- Thaweewat/hc3-24k-th
	- Thaweewat/gpteacher-20k-th
	- Thaweewat/onet-m6-social
	- Thaweewat/alpaca-finance-43k-th
	language:
	- th
	- en
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- openthaigpt
	---

	# 🇹🇭 OpenThaiGPT 0.1.0-beta
	<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2Fb8eiMDaqiEQL6ahbAY0h%2Fimage.png?alt=media&token=6fce78fd-2cca-4c0a-9648-bd5518e644ce
	https://openthaigpt.aieat.or.th/" width="200px">

	OpenThaiGPT Version 0.1.0-beta is a 7B-parameter LLaMA model finetuned to follow Thai translated instructions below and makes use of the Huggingface LLaMA implementation.


	## Support
	- Official website: https://openthaigpt.aieat.or.th
	- Facebook page: https://web.facebook.com/groups/openthaigpt
	- A Discord server for discussion and support [here](https://discord.gg/rUTp6dfVUF)
	- E-mail: kobkrit@iapp.co.th

	## License
	Source Code: License Apache Software License 2.0.<br>
	Weight: For research use only (due to the Facebook LLama's Weight LICENSE).<br>
	<i>Note that: A commercial use license for OpenThaiGPT 0.1.0 weight will be released later soon!</i>

	## Code and Weight
	Finetune Code: https://github.com/OpenThaiGPT/openthaigpt-finetune-010beta<br>
	Inference Code: https://github.com/OpenThaiGPT/openthaigpt<br>
	Weight: https://huggingface.co/kobkrit/openthaigpt-0.1.0-beta

	## Sponsors
	Pantip.com, ThaiSC<br>
	<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2FiWjRxBQgo0HUDcpZKf6A%2Fimage.png?alt=media&token=4fef4517-0b4d-46d6-a5e3-25c30c8137a6" width="100px">
	<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2Ft96uNUI71mAFwkXUtxQt%2Fimage.png?alt=media&token=f8057c0c-5c5f-41ac-bb4b-ad02ee3d4dc2" width="100px">

	### Powered by
	OpenThaiGPT Volunteers, Artificial Intelligence Entrepreneur Association of Thailand (AIEAT), and Artificial Intelligence Association of Thailand (AIAT)

	<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2F6yWPXxdoW76a4UBsM8lw%2Fimage.png?alt=media&token=1006ee8e-5327-4bc0-b9a9-a02e93b0c032" width="100px">
	<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2FBwsmSovEIhW9AEOlHTFU%2Fimage.png?alt=media&token=5b550289-e9e2-44b3-bb8f-d3057d74f247" width="100px">

	### Authors
	Kobkrit Viriyayudhakorn (kobkrit@iapp.co.th), Sumeth Yuenyong (sumeth.yue@mahidol.edu) and Thaweewat Ruksujarit (thaweewr@scg.com).

	<i>Disclaimer: Provided responses are not guaranteed.</i>