CR-Gjx

VL-RLHF

A RLHF Infrastructure for Vision-Language Models

alignment-handbook

Robust recipes to align language models with human and AI preferences

SimPO

SimPO: Simple Preference Optimization with a Reference-Free Reward

chameleon

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

pykan

Kolmogorov Arnold Networks

LLaVA-pp

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

RLHF-Reward-Modeling

Recipes to train reward model for RLHF.

Vitron

A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing

InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的可商用开源多模态对话模型

PLLaVA

Official repository for the paper PLLaVA

AgentBench

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

LLaMA2-Accessory

An Open-source Toolkit for LLM Development

orpo

Official repository for ORPO

Next-Token-Failures

MGM

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

LLaVA-Plus-Codebase

LLaVA-Plus: Large Language and Vision Assistants that Plug and Learn to Use Skills

ToolDec

Syntax Error-Free and Generalizable Tool Use for LLMs via Finite-State Decoding

Muffin

lmms-eval

Accelerating the development of large multimodal models (LMMs) with lmms-eval

lm-human-preference-details

RLHF implementation details of OAI's 2019 codebase

RLHF-APA

RL algorithm: Advantage induced policy alignment

MoE-LLaVA

Mixture-of-Experts for Large Vision-Language Models

LlamaGym

Fine-tune LLM agents with online reinforcement learning

Machine-Learning-Interviews

This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

LLM-FineTuning-Large-Language-Models

LLM (Large Language Model) FineTuning

vstar

PyTorch Implementation of "V* : Guided Visual Search as a Core Mechanism in Multimodal LLMs"

ml-engineering

Machine Learning Engineering Open Book

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

KwaiAgents

A generalized information-seeking agent system with Large Language Models (LLMs).

corr2cause

Data and code for the Corr2Cause paper (ICLR 2024)