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).
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! 👇
No comment highlights available yet. Please check back later!
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.
Attenta was featured in Open Source (68.8k followers), Developer Tools (519k followers), Artificial Intelligence (478.1k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 246.4k products, making this a competitive space to launch in.
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.
Want to see how Attenta stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
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! 👇