Repositories list

• openthairag

  Public
  OpenThaiRAG is an open-source Retrieval-Augmented Generation (RAG) framework designed specifically for Thai language processing. This project combines the power of vector databases, large language models, and information retrieval techniques to provide accurate and context-aware responses to user queries in Thai using OpenThaiGPT 1.5 as LLM.

  pythonragllm+ 1openthaigpt

  Python

  •

  Apache License 2.0

  •6•33•0•0•Updated Dec 13, 2024Dec 13, 2024

• data-processing

  Public
  Python

  •

  Apache License 2.0

  •1•0•0•0•Updated Nov 6, 2024Nov 6, 2024

• openthaigpt1.5_api_examples

  Public
  Python

  •

  Apache License 2.0

  •5•2•0•1•Updated Oct 29, 2024Oct 29, 2024

• PDF2ThaiText

  Public
  Python

  •

  Apache License 2.0

  •0•0•1•0•Updated Sep 27, 2024Sep 27, 2024

• model-evaluation

  Public
  Jupyter Notebook

  •7•0•0•0•Updated Sep 23, 2024Sep 23, 2024

• continue-pretraining

  Public
  Python

  •

  Apache License 2.0

  •0•0•0•0•Updated Sep 23, 2024Sep 23, 2024

• openthaigpt-pretraining

  Public
  Jupyter Notebook

  •

  Apache License 2.0

  •9•21•59•24•Updated May 1, 2024May 1, 2024

• openthaigpt_eval

  Public
  Python

  •

  Apache License 2.0

  •7•21•1•0•Updated Apr 7, 2024Apr 7, 2024

• OpenThaiGPT-Constructing-an-Instruction-based-LLM-from-Highly-Contaminated-Datasets

  Public
  Jupyter Notebook

  •

  Apache License 2.0

  •0•0•0•0•Updated Feb 16, 2024Feb 16, 2024

• openthaigpt-hf-webapp

  Public
  Python

  •

  MIT License

  •0•1•0•0•Updated Feb 14, 2024Feb 14, 2024

• lm-evaluation-harness

  Public
  A framework for few-shot evaluation of autoregressive language models.

  Python

  •

  MIT License

  •2k•0•0•7•Updated Feb 10, 2024Feb 10, 2024

• Seq2Lightning

  Public
  Project based on PyTorch-lightning and Transformers for training Seq2SeqLM models, with a primary focus on MT5 and FLAN-T5, yet not limited to them

  Python

  •

  Apache License 2.0

  •2•0•0•0•Updated Jan 12, 2024Jan 12, 2024

• data-eval-exams-ic

  Public
  0•1•0•0•Updated Jan 6, 2024Jan 6, 2024

• data-eval-exams-onet

  Public
  0•1•0•0•Updated Dec 23, 2023Dec 23, 2023

• openthaigpt-finetune

  Public
  Finetune Code for OpenThaiGPT 0.1.0-beta

  Python

  •

  Apache License 2.0

  •14•12•0•0•Updated Nov 11, 2023Nov 11, 2023

• TinyLlama

  Public
  The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

  Python

  •

  Apache License 2.0

  •490•0•0•0•Updated Oct 7, 2023Oct 7, 2023

• volunteer-exam-ai-application

  Public
  CSS

  •0•0•0•0•Updated Sep 24, 2023Sep 24, 2023

• volunteer-exam-ml-deployment

  Public
  Python

  •0•0•0•0•Updated Sep 24, 2023Sep 24, 2023

• openthaigpt-aieng-exam

  Public
  Python

  •3•0•0•0•Updated Sep 24, 2023Sep 24, 2023

• openthaigpt-dataeng-exam

  Public
  Python

  •0•1•0•0•Updated Sep 24, 2023Sep 24, 2023

• promptsource

  Public
  Toolkit for creating, sharing and using natural language prompts.

  Python

  •

  Apache License 2.0

  •356•0•0•0•Updated Jun 7, 2023Jun 7, 2023

• openthaigpt

  Public
  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.

  Python

  •

  Other

  •20•111•3•0•Updated May 26, 2023May 26, 2023

• datasets

  Public
  Apache License 2.0

  •0•1•0•0•Updated Apr 19, 2023Apr 19, 2023

• openthaigpt-example

  Public
  Example for OpenThaiGPT

  Python

  •

  Apache License 2.0

  •2•4•0•0•Updated Mar 19, 2023Mar 19, 2023

• Open-Assistant

  Public
  Python

  •

  Apache License 2.0

  •8•4•0•0•Updated Feb 28, 2023Feb 28, 2023

• ungoliant-thai

  Public
  🕷️ The pipeline for the OSCAR corpus

  Rust

  •

  Apache License 2.0

  •14•2•0•0•Updated Feb 24, 2023Feb 24, 2023