martin PRO

martintomov

AI & ML interests

None yet

Recent Activity

reacted to merve's post with šŸš€ 7 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 7 days ago
FastVideo/FastMochi
View all activity

Organizations

MLX Community's profile picture RB-IBDM's profile picture Cape's profile picture synthgen's profile picture aiml4fun's profile picture AI Starter Pack's profile picture