Pinned Repositories
VideoLLaMA2
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Algorithm
为了实习与秋招___刷题
CLIP
Contrastive Language-Image Pretraining
hill2hill.github.io
WangPeng的个人主页
LLaVA
Visual Instruction Tuning: Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.
MiniCPM-V
MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone
my_nanoGPT
参看nanoGPT从零重新实现一个
nanoGPT_copy
通过模仿, 学习nanoGPT
OpenCV-handcraft
使用C++实现opencv的各种算法(基于Qt)
pace
日常学习的记录
hill2hill's Repositories
hill2hill/Algorithm
为了实习与秋招___刷题
hill2hill/OpenCV-handcraft
使用C++实现opencv的各种算法(基于Qt)
hill2hill/CLIP
Contrastive Language-Image Pretraining
hill2hill/hill2hill.github.io
WangPeng的个人主页
hill2hill/LLaVA
Visual Instruction Tuning: Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.
hill2hill/my_nanoGPT
参看nanoGPT从零重新实现一个
hill2hill/nanoGPT_copy
通过模仿, 学习nanoGPT
hill2hill/pace
日常学习的记录
hill2hill/paper_summary
对自己阅读的一些论文进行记录
hill2hill/reverse_block
如何才算赢:使拼板全部变成蓝色。 玩法:每个方块一面橙色,一面蓝色。点击一个方块,这个方块的颜色会翻转,并且,与它邻接的方块的颜色也会翻转。
hill2hill/youtube-8m
Code of PhoenixLin(3rd place) in the 2nd Youtube8M Video Understanding Challenge
hill2hill/some_scripts