ai-city-2023-track2

ai-recommendersystem

该仓库尝试整理推荐系统领域的一些经典算法模型

autocompressors

[EMNLP 2023] Adapting Language Models to Compress Long Contexts

bertweet

BERTweet: A pre-trained language model for English Tweets (EMNLP-2020)

ddpm-torch

Unofficial PyTorch Implementation of Denoising Diffusion Probabilistic Models (DDPM)

df-gan

A Simple and Effective Baseline for Text-to-Image Synthesis (CVPR2022 oral)

flash-attention

Fast and memory-efficient exact attention

hands-on-llms

🦖 𝗟𝗲𝗮𝗿𝗻 about 𝗟𝗟𝗠𝘀, 𝗟𝗟𝗠𝗢𝗽𝘀, and 𝘃𝗲𝗰𝘁𝗼𝗿 𝗗𝗕𝘀 for free by designing, training, and deploying a real-time financial advisor LLM system ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 𝘷𝘪𝘥𝘦𝘰 & 𝘳𝘦𝘢𝘥𝘪𝘯𝘨 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭𝘴

heart_disease_classification

kalapa_challenge_2023

Solution Vietnamese Medical Question Answering

l2

latent-diffusion

High-Resolution Image Synthesis with Latent Diffusion Models

latent-diffusion-inpainting

llm-application-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

llm-finetuning-

LLM Finetuning with peft

llm-without-deployment

Practical course about Large Language Models.

medmcqa

A large-scale (194k), Multiple-Choice Question Answering (MCQA) dataset designed to address realworld medical entrance exam questions.

nemo

NeMo: a toolkit for conversational AI

online-examiner

optimizers-code

Optimizer Implementations and Theory for DL

peppa-facial-landmark-pytorch

Facial Landmark Detection based on PyTorch

recbole-cdr

This is a library built upon RecBole for cross-domain recommendation algorithms

scene-text-recognition

Scene Text Recognition on ICDAR2003 dataset

semiautomated-online-examproctoring

B.Tech. Final Year Project by Kunal Gupta, Akshat Jain, Harshita Mishra and Divyam Sharma

stablediffusion-pytorch

This repo implements a Stable Diffusion model in PyTorch with all the essential components.

taming-transformers

Taming Transformers for High-Resolution Image Synthesis

text-to-image-diffusion

Experimental (working!) custom implementation of conditional and unconditional diffusion for testing new methods.

tnt305

vietnamese_llms

Dự án bao gồm: 1. Xây dựng bộ dữ Instructions Vietnamese (chất lượng, nhiều, và đa dạng). 2.LLM Training, Finetuning, Evaluating & Testing trên Open-source mô hình ngôn ngữ: Bloomz,T5, UL2, LLaMA (1&2), OpenLLaMA, GPT-J pythia etc. 3. Ứng dụng và Giao diện Người dùng (UI)

visual-question-answering

Simple Question Answering on Visual COCO Dataset