kiminh

grok-1

Grok open release

mamba

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

gpt-llm-trainer

AIOS

AIOS: LLM Agent Operating System

rank_llm

Repository for prompt-decoding using LLMs (GPT3.5, GPT4, Vicuna, and Zephyr)

logit-standardization-KD

[CVPR 2024 Highlight] Logit Standardization in Knowledge Distillation

InfLLM

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

OpenMatch

An Open-Source Package for Information Retrieval

CIKM2020_DMT

Deep Multifaceted Transformers for Multi-objective Ranking in Large-Scale E-commerce Recommender Systems, CIKM 2020

graph-rag

Graph based retrieval + GenAI = Better RAG in production

quiver-feature

High performance RDMA-based distributed feature collection component for training GNN model on EXTREMELY large graph

Adaptive-MT-LLM-Fine-tuning

Fine-tuning Mistral LLM for Adaptive Machine Translation

ReLLa

Code of Paper "ReLLa: Retrieval-enhanced Large Language Models for Mitigating Long Context Problems in Recommendation".

title2event_baselines

Title2Event: Benchmarking Open Event Extraction with a Large-scale Chinese Title Dataset

LC-Rec

mercari-ml-merrec-pub-us

toyML

Toy Machine Learning Package

LSVCR

QPP-GenRE

LMRS

PDRec

The source code is for the paper: “Plug-in Diffusion Model for Sequential Recommendation” accepted in AAAI 2024 by Haokai Ma, Ruobing Xie, Lei Meng, Xin Chen, Xu Zhang, Leyu Lin and Zhanhui Kang.

alignment-handbook

Robust recipes to align language models with human and AI preferences

DistilledCTR

CTR prediction using knowledge distillation

eis-itransformer

LLMSRec_Syn

Code for Our NAACL Findings 2024 paper "The Whole is Better than the Sum: Using Aggregated Demonstrations in In-Context Learning for Sequential Recommendation"

LLaMA-Factory

Unify Efficient Fine-tuning of 100+ LLMs

M-scan

The implementation of M-scan algorithm

text-generation-inference

IBM development fork of https://github.com/huggingface/text-generation-inference

toyGraph

Toy Graph Learning package, inspired by StellarGraph.