Hugging Face's logo
dinhanhx's picture
9 29 153

dinhanhx

dinhanhx
htdung167's profile picture 21world's profile picture hdnminh's profile picture
Ā·

AI & ML interests

Vision Language

Recent Activity

replied to merve's post 4 days ago
Apollo is a new family of open-source video language models by Meta, where 3B model outperforms most 7B models and 7B outperforms most 30B models šŸ§¶ āœØ the models come in 1.5B https://huggingface.co/Apollo-LMMs/Apollo-1_5B-t32, 3B https://huggingface.co/Apollo-LMMs/Apollo-3B-t32 and 7B https://huggingface.co/Apollo-LMMs/Apollo-7B-t32 with A2.0 license, based on Qwen1.5 & Qwen2 āœØ the authors also release a benchmark dataset https://huggingface.co/spaces/Apollo-LMMs/ApolloBench The paper has a lot of experiments (they trained 84 models!) about what makes the video LMs work āÆļø Try the demo for best setup here https://huggingface.co/spaces/Apollo-LMMs/Apollo-3B they evaluate sampling strategies, scaling laws for models and datasets, video representation and more! > The authors find out that whatever design decision was applied to small models also scale properly when the model and dataset are scaled šŸ“ˆ scaling dataset has diminishing returns for smaller models > They evaluate frame sampling strategies, and find that FPS sampling is better than uniform sampling, and they find 8-32 tokens per frame optimal > They also compare image encoders, they try a variation of models from shape optimized SigLIP to DINOv2 they find https://huggingface.co/google/siglip-so400m-patch14-384 to be most powerful šŸ”„ > they also compare freezing different parts of models, training all stages with some frozen parts give the best yield They eventually release three models, where Apollo-3B outperforms most 7B models and Apollo 7B outperforms 30B models šŸ”„
liked a model 4 days ago
erax-ai/EraX-VL-2B-V1.5
liked a model 10 days ago
HIT-TMG/KaLM-embedding-multilingual-mini-instruct-v1.5
View all activity

Organizations

Blog-explorers's profile picture ZeroGPU Explorers's profile picture Plastanium's profile picture Social Post Explorers's profile picture Hugging Face Discord Community's profile picture

dinhanhx's activity

liked a model 4 days ago
liked 2 models 10 days ago
liked 2 models 11 days ago
liked a model 13 days ago
liked a dataset 14 days ago
liked 2 models 14 days ago
liked a model 21 days ago
liked a model 25 days ago
liked a Space 26 days ago
liked a model 27 days ago
liked 2 models 28 days ago
liked 2 Spaces about 1 month ago
liked a model about 1 month ago
liked 2 models about 2 months ago