#Transformer News.

Transformers now runs llama.cpp quants

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Transformers Explained Visually

An interactive visualization tool showing you how transformer models work in large language models (LLM) like GPT.

A Mathematical Framework for Transformer Circuits (2021)

Hacker News discussion about "A Mathematical Framework for Transformer Circuits (2021)".

On Next-Gen Transformer: Loops Are Not What You Need

Loop Transformer vs Recursive Transformer: why looping blocks is not what next-gen Transformers need, and how composable context turns CoT into thinking about thinking.

GPT-6 Astra, Looped Transformers, and Hidden Reasoning

A Look at Recurrent Depth, Hidden Chains of Thought, and Recent Research on Looping Transformer Blocks

Pathway’s brain-inspired architecture development on Amazon SageMaker HyperPod

Pathway's Baby Dragon Hatchling (BDH) is a brain-inspired, post-transformer architecture that reasons in latent space instead of emitting chain-of-thought tokens. See how Pathway develops and scales BDH on Amazon SageMaker HyperPod, and how BDH-CQ set a new cost-efficiency mark on the ARC-AGI-1 benchmark.

I trained a small transformer in 1.5hrs and it beats many LLMs

Hacker News discussion about "I trained a small transformer in 1.5hrs and it beats many LLMs".

Peter Cullen, Voice of Optimus Prime in 'Transformers,' Dies at 85

Peter Cullen, the voice actor who played Optimus Prime in Transformers films and shows and Eeyore in Winnie the Pooh projects, has died. He was 85.

Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Show HN: A tiny LLM running at 21,000 tok/s on a $250 FPGA (Live Demo)

A 3.16M-parameter INT4 transformer running entirely in the on-chip memory of a Xilinx Kria KV260. Zero DRAM in the token loop, 59,965 tok/s on the fabric, bit-exact. Chat with it live.

Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-Design

Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design. Project website.

Show HN: I built a web tool to see and edit what an AI thinks before it answers

I run a small AI lab and playground and got super excited about Anthropics paper "Verbalizable Representations Form a Global Workspace in Language Models" (https://transformer-circ...

Native-speed vLLM transformers modeling backend

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Is One Layer Enough? A Single Transformer Layer Matches Full-Parameter RL Train

Abstract page for arXiv paper 2607.01232: Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

DiScoFormer: One transformer for density and score, across distributions

A Blog post by Ai2 on Hugging Face

Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModel

A Blog post by NVIDIA on Hugging Face

Experimenting with the proposed Cross-Origin Storage API in Transformers.js

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend