wizyoung

ChuanhuChatGPT

GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.

pelican

Static site generator that supports Markdown and reST syntax. Powered by Python.

Awesome-Chinese-LLM

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

unsloth

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

GPT-4-LLM

Instruction Tuning with GPT-4

AnyText

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

mPLUG-DocOwl

mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding

JetMoE

Reaching LLaMA2 Performance with 0.1M Dollars

lmms-eval

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

Bunny

A family of lightweight multimodal models.

LLaVA-pp

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

TransGPT

LLaVA-NeXT

honeybee

Official implementation of project Honeybee (CVPR 2024)

qwen-free-api

🚀 阿里通义千问2.5大模型逆向API白嫖测试【特长：六边形战士】，支持高速流式输出、无水印AI绘图、长文档解读、图像解析、多轮对话，零配置部署，多路token支持，自动清理会话痕迹。

Tabular-LLM

本项目旨在收集开源的表格智能任务数据集（比如表格问答、表格-文本生成等），将原始数据整理为指令微调格式的数据并微调LLM，进而增强LLM对于表格数据的理解，最终构建出专门面向表格智能任务的大型语言模型。

SEED-X

Multimodal Models in Real World

MoAI

Official PyTorch implementation code for realizing the technical part of Mixture of All Intelligence (MoAI) to improve performance of numerous zero-shot vision language tasks. (Under Review)

scaling_on_scales

When do we not need larger vision models?

font

ChartVLM

Official Repository of ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning

FastV

Code for paper: An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

VILA

VILA - A multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

MathVerse

Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?

G-LLaVA

Official github repo of G-LLaVA

CuMo

CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts

summarize_from_feedback_details

VW-LMM

mamba-gpt-3b

It is almost the best 3B model in the current open source industry, surpassing Dolly v2-3b, open lama-3b, and even outperforming the EleutherAI/pythia-12b model in terms of performance. Can refer to open_llm_leaderboard

ocr-dataset-rendering