This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
Attenta
A from-scratch Rust Transformer trained on legal documents
Attenta is a from-scratch Rust implementation of the Transformer architecture (Vaswani et al. 2017) built without PyTorch or TensorFlow. Designed for high efficiency, it features multi-head attention, BPE tokenization, and custom matrix multiplication. This release comes pre-trained on Indian legal documents, showcasing a pure Rust pipeline for specialized NLP tasks from tokenization to beam search decoding. Fully tested with 85 unit tests and ready to self-host.
I'm the creator of Attenta. I wanted to see how far I could push pure Rust for deep learning architectures without relying on massive frameworks like PyTorch or TensorFlow.
Attenta is a complete, from-scratch implementation of the original "Attention Is All You Need" Transformer paper. To make it a true end-to-end proof of concept, I trained it specifically on structured Indian legal documents.
Key features engineered directly into the crate:
• Custom BPE tokenization & bucket batching
• Multi-head attention with optimized 64x64 blocked matmul for cache efficiency
• Adam optimizer with warmup schedules & label smoothing
• 85 unit tests covering everything from scratch
Whether you love Rust, are curious about zero-dependency AI, or work in legal tech, I'd love for you to check out the repository, run the training scripts, and let me know your thoughts!
What features or optimization techniques should I implement next? Let me know below! 👇
About Attenta on Product Hunt
“A from-scratch Rust Transformer trained on legal documents”
Attenta was submitted on Product Hunt and earned 8 upvotes and 1 comments, placing #32 on the daily leaderboard. Attenta is a from-scratch Rust implementation of the Transformer architecture (Vaswani et al. 2017) built without PyTorch or TensorFlow. Designed for high efficiency, it features multi-head attention, BPE tokenization, and custom matrix multiplication. This release comes pre-trained on Indian legal documents, showcasing a pure Rust pipeline for specialized NLP tasks from tokenization to beam search decoding. Fully tested with 85 unit tests and ready to self-host.
On the analytics side, Attenta competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how Attenta performed against the three products that launched closest to it on the same day.
Who hunted Attenta?
Attenta was hunted by Meet Mendapara. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Attenta including community comment highlights and product details, visit the product overview.
Meet Mendapara
Hey Product Hunt community! 👋
I'm the creator of Attenta. I wanted to see how far I could push pure Rust for deep learning architectures without relying on massive frameworks like PyTorch or TensorFlow.
Attenta is a complete, from-scratch implementation of the original "Attention Is All You Need" Transformer paper. To make it a true end-to-end proof of concept, I trained it specifically on structured Indian legal documents.
Key features engineered directly into the crate:
• Custom BPE tokenization & bucket batching
• Multi-head attention with optimized 64x64 blocked matmul for cache efficiency
• Adam optimizer with warmup schedules & label smoothing
• 85 unit tests covering everything from scratch
Whether you love Rust, are curious about zero-dependency AI, or work in legal tech, I'd love for you to check out the repository, run the training scripts, and let me know your thoughts!
What features or optimization techniques should I implement next? Let me know below! 👇