stdKonjac

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

openai-python

The official Python library for the OpenAI API

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

self-rag

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

kinetics-dataset

AnglE

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

Awesome-Healthcare-Foundation-Models

DreamLLM

[ICLR 2024 Spotlight] DreamLLM: Synergistic Multimodal Comprehension and Creation

VQA

AutoCompressors

[EMNLP 2023] Adapting Language Models to Compress Long Contexts

OWL

A Large Language Model for IT Operations

visdial

[CVPR 2017] Torch code for Visual Dialog

visdial-challenge-starter-pytorch

Starter code in PyTorch for the Visual Dialog challenge

SeViLA

[NeurIPS 2023] Self-Chained Image-Language Model for Video Localization and Question Answering

Retrieval-Augmented-Visual-Question-Answering

This is the official repository for Retrieval Augmented Visual Question Answering

llama2-lora-fine-tuning

llama2 finetuning with deepspeed and lora

WSDM-Cup-2024

1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc

NExT-QA

NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR'21)

recomp

RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation.

MAC

Online Adaptation of Language Models with a Memory of Amortized Contexts

ADSampling

[SIGMOD 2023] High-Dimensional Approximate Nearest Neighbor Search: with Reliable and Efficient Distance Comparison Operations

VIP5

MM23-MISSRec

The code for the paper "MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation" (ACM MM'23).

SEMICON

NExT-OE

NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR'21)

ReMuQ

a multimodal retrieval dataset

retriever_reader_for_okvqa

Anima

Moved to here: https://github.com/lyogavin/airllm