60 40 515

martin PRO

martintomov

AI & ML interests

None yet

Recent Activity

liked a model 4 days ago

arnaudstiegler/sd-model-gameNgen-60ksteps

reacted to merve's post with 🚀 8 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 🧶 ✨ 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 ✨ 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 ⏯️ 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 📈 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 🔥 > 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 🔥

liked a model 8 days ago

FastVideo/FastMochi

View all activity

Organizations

martintomov's activity

liked a model 4 days ago

arnaudstiegler/sd-model-gameNgen-60ksteps

Text-to-Image • Updated 12 days ago • 337 • 1

reacted to merve's post with 🚀 8 days ago

Post

2916

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 🧶

✨ 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
✨ 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 ⏯️

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 📈 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 google/siglip-so400m-patch14-384 to be most powerful 🔥
> 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 🔥