Article
🌁#81: Key AI Concepts to Follow in 2025
By
•
•
15youssef boulaouane
byoussef
AI & ML interests
None yet
Recent Activity
upvoted
an
article
2 days ago
🌁#81: Key AI Concepts to Follow in 2025
upvoted
a
collection
18 days ago
Dec 6 Releases 🎄
liked
a model
20 days ago
meta-llama/Llama-3.3-70B-Instruct
Organizations
byoussef's activity
upvoted
an
article
2 days ago
upvoted
a
collection
18 days ago
liked
2
models
20 days ago
liked
a
model
21 days ago
reacted to
merve's
post with 🚀
24 days ago
Post
2631
small but mighty 🔥
you can fine-tune SmolVLM on an L4 with batch size of 4 and it will only take 16.4 GB VRAM 🫰🏻 also with gradient accumulation simulated batch size is 16 ✨
I made a notebook that includes all the goodies: QLoRA, gradient accumulation, gradient checkpointing with explanations on how they work 💝 https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
you can fine-tune SmolVLM on an L4 with batch size of 4 and it will only take 16.4 GB VRAM 🫰🏻 also with gradient accumulation simulated batch size is 16 ✨
I made a notebook that includes all the goodies: QLoRA, gradient accumulation, gradient checkpointing with explanations on how they work 💝 https://github.com/huggingface/smollm/blob/main/finetuning/Smol_VLM_FT.ipynb
liked
a
Space
24 days ago
reacted to
rwightman's
post with 🚀
about 1 month ago
Post
1056
Want to validate some hparams or figure out what
I had this sitting on my drive and forgot where I pulled it together from. It's 100 classes of imagenet, 50k train and 10k val images (from ImageNet-1k train set), and 5k test images (from ImageNet-1k val set). 7.4GB instead of > 100GB for the full ImageNet-1k. This ver is not reduced resolution like some other 'mini' versions. Super easy to use with timm train/val scripts, checkout the dataset card.
I often check fine-tuning with even smaller datasets like:
* timm/resisc45
* timm/oxford-iiit-pet
But those are a bit small to train any modest size model w/o starting from pretrained weights.
timm model to use before commiting to download or training with a large dataset? Try mini-imagenet:
timm/mini-imagenet I had this sitting on my drive and forgot where I pulled it together from. It's 100 classes of imagenet, 50k train and 10k val images (from ImageNet-1k train set), and 5k test images (from ImageNet-1k val set). 7.4GB instead of > 100GB for the full ImageNet-1k. This ver is not reduced resolution like some other 'mini' versions. Super easy to use with timm train/val scripts, checkout the dataset card.
I often check fine-tuning with even smaller datasets like:
* timm/resisc45
* timm/oxford-iiit-pet
But those are a bit small to train any modest size model w/o starting from pretrained weights.
upvoted
a
collection
about 1 month ago
upvoted
a
collection
about 2 months ago
reacted to
averoo's
post with 🔥
about 2 months ago
Post
3790
Hello, researchers! I've tried to made reading HF Daily Papers easier and made a tool that does reviews with LLMs like Claude 3.5, GPT-4o and sometimes FLUX.
📚 Classification by topics
📅 Sorting by publication date and HF addition date
🔄 Syncing every 2 hours
💻 Hosted on GitHub
🌏 English, Russian, and Chinese
📈 Top by week/month (in progress)
👉 https://hfday.ru
Let me know what do you think of it.
📚 Classification by topics
📅 Sorting by publication date and HF addition date
🔄 Syncing every 2 hours
💻 Hosted on GitHub
🌏 English, Russian, and Chinese
📈 Top by week/month (in progress)
👉 https://hfday.ru
Let me know what do you think of it.
upvoted
a
collection
2 months ago
liked
a
model
2 months ago
upvoted
an
article
3 months ago
Article
Welcome, Gradio 5
•
93
liked
a
Space
3 months ago
reacted to
rwightman's
post with ❤️
3 months ago
Post
2509
A 'small' MobileNet-V4 update, I just pushed weights for the smallest model I've trained in the series, a 0.5 width multiplier version of the MobileNet-V4 Conv Small.
Now you may look at this and say hey, why is this impressive? 64.8% top-1 and 2.2M params? MobileNetV3-Small 0.75, and MobileNet-V2 0.5 are both fewer params (at ~2M) and over 65% top-1, what gives? Well this is where MobileNet-V4 differs from the previous versions of the model family, it trades off (gives up) a little parameter efficiency for some computational efficiency.
So, let's look at the speed. On a 4090 w/ torchcompile
* 98K img/sec - timm/mobilenetv4_conv_small_050.e3000_r224_in1k
* 58K img/sec - timm/mobilenetv3_small_075.lamb_in1k
* 37K img/sec - timm/mobilenetv2_050.lamb_in1k
And there you go, if you have a need for speed, MNV4 is the better option.
Now you may look at this and say hey, why is this impressive? 64.8% top-1 and 2.2M params? MobileNetV3-Small 0.75, and MobileNet-V2 0.5 are both fewer params (at ~2M) and over 65% top-1, what gives? Well this is where MobileNet-V4 differs from the previous versions of the model family, it trades off (gives up) a little parameter efficiency for some computational efficiency.
So, let's look at the speed. On a 4090 w/ torchcompile
* 98K img/sec - timm/mobilenetv4_conv_small_050.e3000_r224_in1k
* 58K img/sec - timm/mobilenetv3_small_075.lamb_in1k
* 37K img/sec - timm/mobilenetv2_050.lamb_in1k
And there you go, if you have a need for speed, MNV4 is the better option.
upvoted
an
article
3 months ago
Article
Tiny Test Models
By
•
•
6
upvoted
a
paper
3 months ago
liked
a
Space
4 months ago
upvoted
a
paper
4 months ago