tanyang1231

calculon

MMDU

Official repository of MMDU dataset

threestudio

A unified framework for 3D content generation.

Awesome-Text-to-3D

A growing curation of Text-to-3D, Diffusion-to-3D works.

stable-diffusion

A latent text-to-image diffusion model

FeatUp

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

DALLE-pytorch

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

CogVideo

Text-to-video generation. The repo for ICLR2023 paper "CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers"

Qwen2

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

GLM-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

LLMs_interview_notes

LLMs interview notes and answers:该仓库主要记录大模型（LLMs）算法工程师相关的面试题和参考答案

CogVLM2

GPT4V-level open-source multi-modal model based on Llama3-8B

SegmentationTransferability

Code of ICIP2023 paper: Efficient Prediction of Model Transferability in Semantic Segmentation Tasks

Meteor

Official PyTorch implementation code for realizing the technical part of Mamba-based traversal of rationale (Meteor) to improve performance of numerous vision language performances for diverse capabilities. (Under Review)

sentencepiece_chinese_bpe

使用sentencepiece中BPE训练中文词表，并在transformers中进行使用。

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

LLMs_interview_notes

该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

LVLM-Hallucinations-Survey

docvqa

Document Visual Question Answering

swift

ms-swift: Use PEFT or Full-parameter to finetune 300+ LLMs or 50+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3, Llava-Video, Internvl2, MiniCPM-V, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

PLLaVA

Official repository for the paper PLLaVA

XVERSE-V-13B

InternVL

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

MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

GeneFacePlusPlus

GeneFace++: Generalized and Stable Real-Time 3D Talking Face Generation; Official Code

llama3-Chinese-chat

Llama3 中文仓库（聚合资料，各种网友及厂商微调、魔改版本有趣权重 & 训练、推理、评测、部署教程视频 & 文档）

llm.c

LLM training in simple, raw C/CUDA

FasterDAN

mPLUG-DocOwl

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