phoebussi Goto Github PK

404-3.github.io

acl2020-confidence-regularization

ai-deadlines

:alarm_clock: AI conference deadline countdowns

alpaca-cot

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台，我们欢迎开源爱好者发起任何有意义的pr！

alpaca-cot-ad

audiogpt

awesome-instruction-dataset

awesome-knowledge-distillation

Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2020)。

bert

TensorFlow code and pre-trained models for BERT

bert-pytorch

Google AI 2018 BERT pytorch implementation

bert-textclassification

Implemention some Baseline Model upon Bert for Text Classification

bottom-up-attention-vqa

An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.

cdssm

A PyTorch implementation of CDSSM for intent classification

chat-your-data

coach

Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling (ACL-2020)

cogvideo

Text-to-video generation. The repo for ICLR2023 paper "CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers"

compress-robust-vqa

Code for our EMNLP-2023 paper: "Compressing and Debiasing Vision-Language Models for Visual Question Answering".

css-vqa

Counterfactual Samples Synthesizing for Robust VQA

ctir

Code of our IJCAI2021 paper: "Learning Class-Transductive Intent Representations for Zero-shot Intent Detection"

deepunkid

Deep Unknown Intent Detection with Margin Loss (ACL2019)

deformer

[ACL 2020] DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering

detgpt

dialogstudio

DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI

dolly

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

dpr

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

fastchat

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

fastedit

🩹Editing large language models within 10 seconds⚡

flagembedding

Retrieval and Retrieval-augmented LLMs

generalization-causality

关于domain generalization，domain adaptation，causality，robutness，prompt，optimization，generative model各式各样研究的阅读笔记

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.