OpenThaiGPT focuses on developing a Thai Chatbot system to have capabilities equivalent to ChatGPT, as well as being able to connect to external systems and be able to retrieve data flexibly. Easily expandable and customizable and developed into Free open source software for everyone.
Project description
OpenThaiGPT
OpenThaiGPT focuses on developing a Thai Chatbot system to have capabilities equivalent to ChatGPT, as well as being able to connect to external systems and be able to retrieve data flexibly. Easily expandable and customizable and developed into Free open source software for everyone.
- Free software: Apache Software License 2.0
- Project Homepage: https://openthaigpt.aieat.or.th
- Documentation: https://openthaigpt.readthedocs.io
Versions
-
OpenThaiGPT chat inference library (this repository): version 0.1.1
-
Released models
-
kobkrit/openthaigpt-0.1.0-beta
- Pretraining Model: Facebook Llama (7 billion params)
- Dataset: 200,000 Various Translated Instruction Dataset
- RLHF: None
- Minimium Requirement: Nvidia T4 16GB
-
kobkrit/openthaigpt-0.1.0-alpha
- Pretraining Model: ByT5-XL (3.74 billion params)
- Dataset: 50,000 Thai SelfInstruct
- RLHF: None
- Minimium Requirement: Nvidia A100 40GB
-
kobkrit/openthaigpt-gpt2-instructgpt-poc-0.0.4
- Pretraining Model: GPT-2 Thai-base
- InstructDataset: 300,000 Pantip + 5,000 Wiki QA => 12,920 Thai InstructGPT
- RLHF: None
- Minimium Requirement: CPU or Nvidia GTX 1060 6GB
-
kobkrit/openthaigpt-gpt2-instructgpt-poc-0.0.3
- Pretraining Model: GPT-2 Thai-base
- InstructDataset: 300,000 Pantip + 5,000 Wiki QA => 7,000 Thai InstructGPT
- RLHF: None
- Minimium Requirement: CPU or Nvidia GTX 1060 6GB
-
kobkrit/openthaigpt-gpt2-instructgpt-poc-0.0.2
- Pretraining Model: GPT-2 Thai-base
- InstructDataset: 7,000 Thai InstructGPT
- RLHF: None
- Minimium Requirement: CPU or Nvidia GTX 1060 6GB
-
kobkrit/openthaigpt-gpt2-instructgpt-poc-0.0.1
- Pretraining Model: GPT-2 Thai-base
- InstructDataset: 298,678 QA Pairs getting from 70,000 Pantip katoos + Wikipedia QA by iApp
- RLHF: None
- Minimium Requirement: CPU or Nvidia GTX 1060 6GB
-
Installation
Python>=3.6
CPU-Only
$ pip install openthaigpt torch --extra-index-url https://download.pytorch.org/whl/cpu
With GPU
CUDA 11.6
$ pip install openthaigpt torch --extra-index-url https://download.pytorch.org/whl/cu116
CUDA 11.7
$ pip install openthaigpt torch
Using 0.1.0-beta model
import openthaigpt
print(openthaigpt.generate(instruction="แปลภาษาอังกฤษเป็นภาษาไทย", input="We want to reduce weight.", model_name = "kobkrit/openthaigpt-0.1.0-beta", min_length=50, max_length=300, top_p=0.75, top_k=40, num_beams=1, no_repeat_ngram_size=0, temperature=0.1, early_stopping=True, load_8bit=False))
Using 0.1.0-alpha model
import openthaigpt
print(openthaigpt.generate(instruction="แปลภาษาอังกฤษเป็นภาษาไทย", input="We want to reduce weight.", model_name = "kobkrit/openthaigpt-0.1.0-alpha", min_length=50, max_length=300, top_k=20, num_beams=5, no_repeat_ngram_size=20, temperature=1, early_stopping=True))
Usage 0.0.1-0.0.4 model
import openthaigpt
print(openthaigpt.generate("Q: อยากลดความอ้วนทำไง\n\nA:", model_name = "kobkrit/openthaigpt-gpt2-instructgpt-poc-0.0.4"))
print(openthaigpt.zero("การลดน้ำหนักเป็นเรื่องที่ต้องพิจารณาอย่างละเอียดและรอบคอบเพื่อให้ได้ผลลัพธ์ที่ดีและมีประสิทธิภาพมากที่สุด"))
Sponsored by
- Pantip.com
- ThaiSC
Collaborated By
- Artificial Intelligence Entrepreneur Association of Thailand (AIEAT)
- Artificial Intelligence Association of Thailand (AIAT)
Supported By
- NECTEC
- iApp Technology
- NVIDIA
- Microsoft
- Mahidol University
- Gitbook
History
0.1.1 (2023-05-26)
- Add Model version 0.1.0-beta (https://huggingface.co/kobkrit/openthaigpt-0.1.0-beta)
0.1.0 (2023-04-23)
- Support Model Selection
- Add Model version 0.1.0-alpha (https://huggingface.co/kobkrit/openthaigpt-0.1.0-alpha) to supported models.
0.0.9 - 0.0.10 (2023-03-19)
- Release OpenThaiGPT Zero
0.0.8 (2023-03-12)
- Update Readme
0.0.7 (2023-03-12)
- Update Model to Version 0.0.4 (https://huggingface.co/kobkrit/openthaigpt-gpt2-instructgpt-poc-0.0.4)
0.0.6 (2023-03-05)
- Update README
0.0.5 (2023-02-28)
- First release on PyPI.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file openthaigpt-0.1.1.tar.gz
.
File metadata
- Download URL: openthaigpt-0.1.1.tar.gz
- Upload date:
- Size: 11.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.14.0 pkginfo/1.9.6 requests/2.27.1 setuptools/61.2.0 requests-toolbelt/0.10.1 tqdm/4.64.0 CPython/3.9.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5c648f4afbb276da5207eb1ab428f5bf0c1576801787c8232698026cdde47b33 |
|
MD5 | cbd4ff006e00343fbaa0d34b8bcf678e |
|
BLAKE2b-256 | 4a719aa6ea50470c6e5154cc736a2b65f4a488b21c3f59d890543f3ce3b4357b |
File details
Details for the file openthaigpt-0.1.1-py2.py3-none-any.whl
.
File metadata
- Download URL: openthaigpt-0.1.1-py2.py3-none-any.whl
- Upload date:
- Size: 6.1 kB
- Tags: Python 2, Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.14.0 pkginfo/1.9.6 requests/2.27.1 setuptools/61.2.0 requests-toolbelt/0.10.1 tqdm/4.64.0 CPython/3.9.12
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d5f128ed1f768cef2b93af0329ef6e7e38c5fb3a9b2cd65141e82e1d1aa0267d |
|
MD5 | b44e3209da92183dcbdec22305632ab1 |
|
BLAKE2b-256 | e220eaaeed6d9d083aa6c4d2a42cd14327d5b040652f043fdde26c5ae5d5385f |