News
ReleasesOVHcloud unveils Olala mini, its first in-house LLMChinaA 9B model beats a 1T model on FinQA, trained with Crusoe Managed RLReleasesThe internal metaphysics of an LLMReleasesMapping Language Model Internal Representations to Physical Laws and Scientific ReasoningResearchCan China keep rogue AI in check? Meet the start-up testing the top modelsFrontierMicrosoft aims to challenge OpenAI, Anthropic with cheaper, specialized AI modelsOpen modelsMicrosoft rolls out new first-party models and updates to agentic AI continuous improvementFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIFrontierGoogle is making it easier to opt out of Gemini AI model training – here’s howFrontierOpenAI Unveils New Astra AI Model After Scrapping Prior ReleaseReleasesOVHcloud unveils Olala mini, its first in-house LLMChinaA 9B model beats a 1T model on FinQA, trained with Crusoe Managed RLReleasesThe internal metaphysics of an LLMReleasesMapping Language Model Internal Representations to Physical Laws and Scientific ReasoningResearchCan China keep rogue AI in check? Meet the start-up testing the top modelsFrontierMicrosoft aims to challenge OpenAI, Anthropic with cheaper, specialized AI modelsOpen modelsMicrosoft rolls out new first-party models and updates to agentic AI continuous improvementFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIFrontierGoogle is making it easier to opt out of Gemini AI model training – here’s howFrontierOpenAI Unveils New Astra AI Model After Scrapping Prior Release
EveryLLM

Dense decoder transformers

The GPT design: one stack of transformer layers predicting the next token. 308 models on EveryLLM so far.

The dense decoder transformer is the design behind GPT and most chatbots. It is a single stack of identical transformer layers that reads the tokens so far and predicts the next one, with a mask that stops each position from looking ahead. Dense means every parameter is used for every token, unlike in a mixture of experts. GPT-3, PaLM, Llama 3, Chinchilla, Gemma, Phi and OLMo are dense decoders.

Inside each layer

Each layer has two parts. Self-attention lets every token weigh every earlier token and gather what it needs; a feed-forward network then transforms each token's vector on its own. The transformer was introduced by Google researchers in the June 2017 paper Attention Is All You Need, for translation, and OpenAI's GPT-1 (2018) kept only its decoder half. Llama 3.1 405B, released in July 2024, stacks 126 such layers.

Why it won

A decoder trains on any text without labels, because the next token is always the answer to predict, and it scales smoothly: scaling laws published by OpenAI in 2020 and DeepMind in 2022 showed the error falling predictably with more parameters, data and compute. Its weak point is cost. Attention grows with the square of the context length, and every parameter must be read for every token, which is why mixtures of experts became popular.

Famous dense decoder models

Still to be written: OLMo (language model).

Further reading

BuddhaBot 🇯🇵 Japan and 1 moreBuddhaBot A chatbot answering questions from early Buddhist textsDomain · Research only · 2021 Claude Mythos 🇺🇸 United StatesClaude Mythos Anthropic's restricted model family for finding software security flawsDomain · Research only · 2026 Med-PaLM 🇺🇸 United StatesMed-PaLM A medical-domain language model aligned from Flan-PaLM using instruction prompt tuning.Domain · Research only · 2022 Med-PaLM 2 🇺🇸 United StatesMed-PaLM 2 Google's medical question-answering model built on PaLM 2Domain · Research only · 2023 Minerva 🇺🇸 United StatesMinerva A language model trained further on technical content to solve maths and science problemsResearch · Research only · 2022 Llama Guard WorldLlama Guard A Llama 2 based model that classifies prompts and replies for safety risksDomain · Open weights · 2023 BioGPT 🇺🇸 United StatesBioGPT A generative Transformer trained on biomedical writing for text and mining tasksDomain · Open weights · 2022 SaulLM-7B WorldSaulLM-7B A 7-billion parameter language model for legal text.Domain · Open weights · 2024 BloombergGPT 🇺🇸 United StatesBloombergGPT A 50 billion parameter language model for finance.Domain · Research only · 2023 Meditron WorldMeditron Open-source medical language models based on Llama-2.Domain · Open weights · 2023 DeepSeekMath 🇨🇳 ChinaDeepSeekMath Open language model for mathematical reasoningReasoning · Open weights · 2024 fnLlemma 🇺🇸 United StatesLlemma Open language model for mathematical reasoningDomain · Open weights · 2023 Tsuzumi 🇯🇵 JapanTsuzumi Lightweight Japanese LLM for business useGeneral · API only · 2024 Baichuan-M2 🇨🇳 ChinaBaichuan-M2 Open-source medical reasoning model with 32 billion parameters.Reasoning · Open weights · 2025 Galactica 🇺🇸 United StatesGalactica A language model trained on scientific text for research tasksDomain · Conditional licence · 2022 Sarvam-Translate 🇮🇳 IndiaSarvam-Translate Document-level translation model for 22 Indian languages.Domain · Fully open imgMedGemma 🇺🇸 United StatesMedGemma Medical vision-language models built on Gemma 3 for images and textMultimodal · Conditional licence · 2025

The weekly digest

Every Monday: the model of the day, new pages on EveryLLM, and the conferences and anniversaries of the week ahead.