JudeLee19

HMNet-End-to-End-Abstractive-Summarization-for-Meetings

"End-to-End Abstractive Summarization for Meetings" paper - Unofficial PyTorch Implementation

alexa-with-dstc10-track2-dataset

DSTC10 Track 2 - Knowledge-grounded Task-oriented Dialogue Modeling on Spoken Conversations

attention_with_linear_biases

Code for the ALiBi method for transformer language models

awesome-scene-understanding

😎 A list of papers for scene understanding in computer vision.

CLIP4Cir

CLIP for Composed image retrieval training code

ConvLab-2

ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems

debug-mistakes-cce

Meaningfully debugging model mistakes with conceptual counterfactual explanations. ICML 2022

decision-transformer

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

fashion-attribute-disentanglement

following-instructions-human-feedback

fuzzywuzzy

Fuzzy String Matching in Python

fvcore

Collection of common code that's shared among different research projects in FAIR computer vision team.

GLM

GLM (General Language Model)

guidance

A guidance language for controlling large language models.

Instruction-Tuning-Papers

Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).

judelee19.github.io

Knover

Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle

Knowldege-Grounded-Conversation

A Knowldege Grounded Conversation (KGC) Paper Reading List Maintained by Shandong University

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

longeval-summarization

Official repository for our EACL 2023 paper "LongEval: Guidelines for Human Evaluation of Faithfulness in Long-form Summarization" (https://arxiv.org/abs/2301.13298).

lq-lora

MinTL

MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems

PaLM-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

self-rag

SimpleReDial-v1

The sources codes of the DR-BERT model and baselines

summarize-from-feedback

Code for "Learning to summarize from human feedback"

task_vectors

Editing Models with Task Arithmetic

the-pile

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs