TiantZhang

AICITY2024_Track2_AliOpenTrek_CityLLaVA

Bumblebee

A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.

ego4d_asl

code for Ego4D Workshop@CVPR 2023 - 1st in MQ & 2nd in NLQ challenge

HuggingFace-Download-Accelerator

利用HuggingFace的官方下载工具从镜像网站进行高速下载。

InternVideo2

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

mobilenetv3

mobilenetv3 with pytorch，provide pre-train model

Multi-camera-People-Tracking-With-Mixture-of-Realistic-and-Synthetic-Knowledge

Official codes of the second place for The AI City Challenge 2023 Track 1

SCB-dataset

Student Classroom Behavior dataset

Telechat

TiantZhang/AICITY2024_Track2_AliOpenTrek_CityLLaVA

TiantZhang/Bumblebee

A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.

TiantZhang/ego4d_asl

code for Ego4D Workshop@CVPR 2023 - 1st in MQ & 2nd in NLQ challenge

TiantZhang/HuggingFace-Download-Accelerator

利用HuggingFace的官方下载工具从镜像网站进行高速下载。

TiantZhang/InternVideo2

TiantZhang/LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

TiantZhang/mobilenetv3

mobilenetv3 with pytorch，provide pre-train model

TiantZhang/Multi-camera-People-Tracking-With-Mixture-of-Realistic-and-Synthetic-Knowledge

Official codes of the second place for The AI City Challenge 2023 Track 1

TiantZhang/SCB-dataset

Student Classroom Behavior dataset

TiantZhang/Telechat

TiantZhang/ViP-LLaVA

ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts