Stars
A platform independent standalone library that plays Lottie Animation.
MINT-1T: A one trillion token multimodal interleaved dataset.
A collection of localized (Korean) AWS AI/ML workshop materials for hands-on labs.
Code for "Jhamtani H.*, Gangal V.*, Hovy E. and Nyberg E. Shakespearizing Modern Language Using Copy-Enriched Sequence to Sequence Models" Workshop on Stylistic Variation, EMNLP 2017
This is the Grammarly's Yahoo Answers Formality Corpus
Paper List for Style Transfer in Text
Google for Games Generative AI Quickstart
A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM
Windows system utilities to maximize productivity
18 Lessons, Get Started Building with Generative AI ๐ https://microsoft.github.io/generative-ai-for-beginners/
A compute framework for building Search, RAG, Recommendations and Analytics over complex (structured+unstructured) data, with ultra-modal vector embeddings.
Awesome-llm-role-playing-with-persona: a curated list of resources for large language models for role-playing with assigned personas
Official Python library for the DeepL language translation API.
KoAlpaca: ํ๊ตญ์ด ๋ช ๋ น์ด๋ฅผ ์ดํดํ๋ ์คํ์์ค ์ธ์ด๋ชจ๋ธ
KoRean based SBERT pre-trained models (KR-SBERT) for PyTorch
This is code for paper: MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction
Must-read papers on prompt-based tuning for pre-trained language models.
A collection of Knowledge Tracing model implementations with PyTorch
๐ค PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
Analysis of Story-Cloze-Test (SCT) task and its training set (ROCStories). History, developments and future works.
KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding
The source code demos for the yFiles for HTML diagramming library
Use commands in English to control Blender with OpenAI's GPT-4
Data and download script to accompany LREC2020 paper "Automated Fact-Checking of Claims from Wikipedia"