Hugging Face's logo
Daniel Bourke's picture
20 240 874

Daniel Bourke PRO

mrdbourke
13sushi's profile picture urameez's profile picture vaibhavrana's profile picture
Ā·
https://www.mrdbourke.com

AI & ML interests

Computer vision. Small on-device models. VLMs. High-quality tutorials.

Recent Activity

upvoted a paper about 14 hours ago
FastVLM: Efficient Vision Encoding for Vision Language Models
reacted to IlyasMoutawwakil's post with šŸ”„ about 22 hours ago
After 2 months of refinement, I'm happy to announce that a lot of Transformers' modeling code is now significantly more torch-compile & export-friendly šŸ”„ Why it had to be done šŸ‘‡ PyTorch's Dynamo compiler is increasingly becoming the default interoperability layer for ML systems. Anything that relies on torch.export or torch.compile, from model optimization to cross-framework integrations, benefits directly when models can be captured as a single dynamo-traced graph ! Transformers models are now easier to: āš™ļø Compile end-to-end with torch.compile backends šŸ“¦ Export reliably via torch.export and torch.onnx.export šŸš€ Deploy to ONNX / ONNX Runtime, Intel Corporation's OpenVINO, NVIDIA AutoDeploy (TRT-LLM), AMD's Quark, Meta's Executorch and more hardware-specific runtimes. This work aims at unblocking entire TorchDynamo-based toolchains that rely on exporting Transformers across runtimes and accelerators. We are doubling down on Transformers commitment to be a first-class citizen of the PyTorch ecosystem, more exportable, more optimizable, and easier to deploy everywhere. There are definitely some edge-cases that we still haven't addressed so don't hesitate to try compiling / exporting your favorite transformers and to open issues / PRs. PR in the comments ! More updates coming coming soon !
reacted to danielhanchen's post with ā¤ļø about 22 hours ago
You can now fine-tune embedding models in our free Unsloth notebook! šŸ¤— Fine-tuning embedding models improves retrieval & RAG by aligning vectors to your domain-specific notion of similarity, improving search, clustering, and recommendations on your data. ā­ Blog + Notebooks: https://unsloth.ai/docs/new/embedding-finetuning Unsloth trains embedding models 1.8-3.3x faster with 20% less VRAM, 2x longer context & no accuracy loss vs. FA2 setups. We'd like to thank Hugging Face and Unsloth contributor: electroglyph for making this possible!
View all activity

Organizations

None yet