Hackernews posts about Transformer

Transformer is a type of neural network architecture designed for natural language processing tasks that relies on self-attention mechanisms to process input sequences in parallel.

RSS feed for Transformer

Related:Apple

91
newTransformers Explained Visuallypoloclub.github.io
▲ 661aray07 11d 💬 92
92
newGPT-6 Astra, looped transformers, and hidden reasoningmagazine.sebastianraschka.com
▲ 521ModelForge 23d 💬 162
93
newA Mathematical Framework for Transformer Circuits (2021)transformer-circuits.pub
▲ 107Bluestein 21d 💬 17
94
newPSSA: A non-transformer language model written from scratch in Rustgithub.com
▲ 88sparticle62 3d 💬 38
95
newShow HN: TurboGPT: train 22KiB transformer in 13sgithub.com
▲ 56lostmsu 3d 💬 10
96
newHitachi to double US production of small and medium-sized power transformerswww.utilitydive.com
▲ 37JumpCrisscross 5d 💬 20
97
newOn Next-Gen Transformer: Loops Are Not What You Needzartbot.github.io
▲ 26matt_d 22d 💬 1
98
newRecurrent Looped Transformeryifanzhang-pro.github.io
▲ 15MayCXC 20d 💬 8
99
newLLM Visualizer – Build a Transformer from Scratchjayvisaria.github.io
▲ 13evo_9 22d 💬 4
100
newTransformers Won't End the Human Race Lolwww.stephendiehl.com
▲ 7ibobev 8d 💬 2
101
newShow HN: Bypassing Transformer Softmax via Static Contractiongithub.com
▲ 7PJHkorea 21d discuss
102
newLooped Transformers as Programmable Computers (2023)arxiv.org
▲ 4peter_d_sherman 23d 💬 1
103
newTransformers now runs llama.cpp quantshuggingface.co
▲ 4mmis1000 10d discuss
104
newLean Verified Transformerssrush.github.io
▲ 4matt_d 11d discuss
105
newDesigning a TPU and optimizing transformer inference on a $100 FPGAim-afan.github.io
▲ 4andrewkongfan 16d discuss
106
new3D viz of how DeepSeek Flash v4.1 is different from decode only transformerwhip.run
▲ 4samagra14 19d discuss
107
newZ1T: Sparse Transformer‑Like Models for Probabilistic Hardwareextropic.ai
▲ 3frozenseven 28d 💬 1
108
newPretraining Latent Information Feedback Transformers with Teacher Supervisionarxiv.org
▲ 3gmays 41h discuss
109
newBeyond LLMs: A Post-Transformer World Emergescacm.acm.org
▲ 3yarapavan 3d discuss
110
newTransformer Can Hold Two Thoughts at Once: Evidence of Lineararxiv.org
▲ 3sbulaev 7d discuss
111
newOpenAI Astra and Recurrent Depth / Looped Transformers [Seb Raschka] [video]www.youtube.com
▲ 2mdp2021 29d 💬 1
112
newPSSA: A non-transformer language model written from scratch in Rustai-news-site-cyan.vercel.app
▲ 2qrify_app 2d discuss
113
newOpenZL v0.3.0: a major upgrade of native LZ engine and Compression Transformergithub.com
▲ 2ksec 2d discuss
114
newTransformers now runs llama.cpp quantshuggingface.co
▲ 2vertigoruntime 11d discuss
115
newThe Basics of Transformer Inferencejax-ml.github.io
▲ 2aray07 11d discuss
116
newDiscovering Interpretable Algorithms by Decompiling Transformers to RASP [video]www.youtube.com
▲ 2matt_d 17d discuss
117
newRecurrent Looped Transformeryifanzhang-pro.github.io
▲ 2meffmadd 19d discuss
118
newTSTY Compact Transformer Substation from China Manufacturer – TSTYwww.tstynice.com
▲ 2gssngsngdh 24d discuss
119
newTransformer-Like Models for Z1extropic.ai
▲ 2gmays 24d discuss
120
newTransformers Are Efficient Compilers, Provablyarxiv.org
▲ 2Bluestein 26d discuss