tqfang

complex-commonsense-reasoning

AIgrads

This is a niche collection of research papers which are proven to be gradients pushing the field of Natural Language Processing, Deep Learning and Artificial Intelligence

aligner

Achieving Efficient Alignment through Learned Correction

petastorm

Petastorm library enables single machine or distributed training and evaluation of deep learning models from datasets in Apache Parquet format. It supports ML frameworks such as Tensorflow, Pytorch, and PySpark and can be used from pure Python code.

PyParquetLoaders

Easy, efficient and Pythonic data loading of Parquet files for PyTorch-based libraries

learning_to_retrieve_reasoning_paths

The official implementation of ICLR 2020, "Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering".

StoryAnalogy

This repo contains the dataset and code in the EMNLP'23 paper: StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding.

UReader

SEED

Official implementation of SEED-LLaMA (ICLR 2024).

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

CogVLM

a state-of-the-art-level open visual language model | 多模态预训练模型

nougat-replication

A full codebase for replicating the results of Nougat from downloading arXiv dataset to the final evaluation. It also contains a few fixes to the original codebase.

pix2struct

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

GPT-SoVITS

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

SPIN

The official implementation of Self-Play Fine-Tuning (SPIN)

AgentLLM

AgentLLM is a PoC for browser-native autonomous agents

meditron

Meditron is a suite of open-source medical Large Language Models (LLMs).

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

weak-to-strong

debias

Methods of training NLP models to ignored biased strategies

Multimodal-AND-Large-Language-Models

Paper list about multimodal and large language models, only used to record papers I read in the daily arxiv for personal needs.

natural-instructions

Expanding natural instructions

reporting_bias_lms

Do pre-trained LMs suffer from reporting bias?

awesome-llm-attributions

A Survey of Attributions for Large Language Models

AbsPyramid

Official code repository for the paper: AbsPyramid: Benchmarking the Abstration Ability of Language Models with a Unified Entailment Graph

KG-LLM-Papers

[Paper List] Papers integrating knowledge graphs (KGs) and large language models (LLMs)

bias-amplification-paradox

MeZO

[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333