airsyuan Goto Github PK

auto-gpt

An experimental open-source attempt to make GPT-4 fully autonomous.

bge

bge推理优化相关脚本

build-chatgpt-website

1.搭建自己的在线的chatgpt网站 2.通过自己的网站对用户按量收费 在线体验：http://www.online-gpt5.com/

chatdoctor

chatglm-6b

ChatGLM-6B：开源双语对话语言模型 | An Open Bilingual Dialogue Language Model

chatglm-finetuning

基于ChatGLM-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning等

chatgpt-mirai-qq-bot

🚀 一键部署！真正的 AI 聊天机器人！支持ChatGPT、文心一言、Bing、Bard、ChatGLM、POE，多账号，人设调教，虚拟女仆、图片渲染、语音发送 | 支持 QQ、Telegram、Discord 等平台

chatpaper

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

chinesesquad

中文机器阅读理解数据集

document-dataset

The dataset for documentQA

grounded-segment-anything

Marrying Grounding DINO with Segment Anything & Stable Diffusion & BLIP - Automatically Detect , Segment and Generate Anything with Image and Text Inputs

homework

llm_stablediffusion_studio

smart chinese LLm

multimedia_actionprediction_project3

Generative Adversarial Network have an extensive use in generating images, faces etc. The same network has an application in predicting next frame. Here we show the next action prediction using GANs

next-prediction

Code and model for "Peeking into the Future: Predicting Future Person Activities and Locations in Videos", Liang et al, CVPR 2019

semantics-assistedvideocaptioning

Source code for Semantics-Assisted Video Captioning Model Trained with Scheduled Sampling Strategy

sina_analysis

利用微博热点话题舆情聚类分析

supcontrast

PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

tackling-modality-heterogeneity

Tackling Modality Heterogeneity with Multi-View Calibration Network for Multimodal Sentiment Detection

typography-with-decor

Typography with Decor: Intelligent Text Style Transfer. CVPR 2019.

video_inbetweening

Tensorflow implementation of paper "From Here to There: Video Inbetweening Using Direct 3D Convolutions" https://arxiv.org/pdf/1905.10240.pdf

zero_nlp

中文nlp应用(大模型、数据、模型、训练、推理)