authurlord

outlines

Structured Text Generation

BUAAThesis

北航研究生学位论文模板（Word+LaTeX）.

DADER

DiffPrep

Train_Transformers_with_INT4

DataInf

DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)

pyDVL

pyDVL is a library of stable implementations of algorithms for data valuation and influence function computation

qingwu-zimu

青梧字幕是一款基于whisper的AI字幕提取工具

starmie

Resources for PVLDB 2023 submission

llama2-raven

LLaMA-Adapter

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

DeepBlocker

Repository for performing Blocking using Deep Learning based on the paper "Deep Learning for Blocking in Entity Matching: A Design Space Exploration"

segmoe

FuseAI

FuseAI Project

BCEmbedding

Netease Youdao's open-source embedding and reranker models for RAG products.

json_repair

A python module to repair invalid JSON, commonly used to parse the output of LLMs

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

MFTCoder

High Accuracy and efficiency multi-task fine-tuning framework for Code LLMs. This work has been accepted by KDD 2024.

rtp-llm

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

icl_task_vectors

LLaMA-Pro

[ACL 2024] Progressive LLaMA with Block Expansion.

e5-mistral-7b-instruct

Finetune mistral-7b-instruct for sentence embeddings

IPM

Repo - Paper "Capturing Semantics for Imputation with Pre-trained Language Models." [ICDE 2021]

MixtralKit

A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI

adapters

A Unified Library for Parameter-Efficient and Modular Transfer Learning

MergeLM

Codebase for Merging Language Models (ICML 2024)

fastmoe

A fast MoE impl for PyTorch

mergekit

Tools for merging pretrained large language models.

lorahub

The official repository of paper "LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition".