|
--- |
|
license: apache-2.0 |
|
language: |
|
- th |
|
- en |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
tags: |
|
- openthaigpt |
|
- llama |
|
--- |
|
|
|
# 🇹🇭 OpenThaiGPT 13b 1.0.0-beta Chat with 16 bits in Huggingface's format. |
|
<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 13b Version 1.0.0-beta is a Thai language 13B-parameter LLaMA v2 Chat model finetuned to follow Thai translated instructions and extend more than 10,000 most popular Thai words vocabularies into LLM's dictionary for turbo speed. |
|
|
|
## Licenses |
|
**Source Code**: License Apache Software License 2.0.<br> |
|
**Weight**: Research and **Commercial uses**.<br> |
|
|
|
## Codes and Weight |
|
**Finetune Code**: https://github.com/OpenThaiGPT/openthaigpt-finetune-010beta<br> |
|
**Inference Code**: https://github.com/OpenThaiGPT/openthaigpt<br> |
|
**Weight (Huggingface Checkpoint)**: https://huggingface.co/openthaigpt/openthaigpt-1.0.0-beta-13b-chat-hf |
|
|
|
## Sponsors |
|
<img src="/static-proxy?url=https%3A%2F%2Fcdn-uploads.huggingface.co%2Fproduction%2Fuploads%2F5fcd9c426d942eaf4d1ebd30%2F42d-GioSs4evIdNuMAaPB.png%26quot%3B%3C%2Fspan%3E width="600px"> |
|
|
|
## Supports |
|
- 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: [email protected] |
|
|
|
## Description |
|
Prompt format is Llama2 |
|
``` |
|
<s>[INST] <<SYS>> |
|
system_prompt |
|
<</SYS>> |
|
|
|
question [/INST] |
|
``` |
|
System prompt: |
|
You are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด |
|
|
|
## How to use |
|
|
|
1. install VLLM (https://github.com/vllm-project/vllm) |
|
2. python -m vllm.entrypoints.api_server --model /path/to/model --tensor-parallel-size num_gpus |
|
3. run inference (CURL example) |
|
|
|
``` |
|
curl --request POST \ |
|
--url http://localhost:8000/generate \ |
|
--header "Content-Type: application/json" \ |
|
--data '{"prompt": "<s>[INST] <<SYS>>\nYou are a question answering assistant. Answer the question as truthful and helpful as possible คุณคือผู้ช่วยตอบคำถาม จงตอบคำถามอย่างถูกต้องและมีประโยชน์ที่สุด\n<</SYS>>\n\nอยากลดความอ้วนต้องทำอย่างไร [/INST]","use_beam_search": false, "temperature": 0.1, "max_tokens": 512, "top_p": 0.75, "top_k": 40, "frequency_penalty": 0.3 "stop": "</s>"}' |
|
``` |
|
|
|
### Authors |
|
* Kobkrit Viriyayudhakorn ([email protected]) |
|
* Sumeth Yuenyong ([email protected]) |
|
* Thaweewat Rugsujarit ([email protected]) |
|
* Jillaphat Jaroenkantasima ([email protected]) |
|
* Norapat Buppodom ([email protected]) |
|
* Koravich Sangkaew ([email protected]) |
|
* Peerawat Rojratchadakorn ([email protected]) |
|
* Surapon Nonesung ([email protected]) |
|
* Chanon Utupon ([email protected]) |
|
* Sadhis Wongprayoon ([email protected]) |
|
* Nucharee Thongthungwong ([email protected]) |
|
* Chawakorn Phiantham ([email protected]) |
|
* Patteera Triamamornwooth ([email protected]) |
|
* Nattarika Juntarapaoraya ([email protected]) |
|
* Kriangkrai Saetan ([email protected]) |
|
* Pitikorn Khlaisamniang ([email protected]) |
|
|
|
<i>Disclaimer: Provided responses are not guaranteed.</i> |
|
|
