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

Encoder-only

BERT and its family: read the whole text at once to understand it. 22 models on EveryLLM so far.

Encoder-only models read a whole text in both directions at once and output a vector for each token, rather than generating text. Trained to fill in masked words, they learn rich representations of meaning and are then fine-tuned for classification, picking out names and places, question answering and search. Google's BERT (2018) defined the type; RoBERTa, ALBERT, DistilBERT, ELECTRA and multilingual variants followed.

Masked language modelling

BERT hides about 15% of the tokens in each training passage and learns to predict them from the words on both sides, which a left-to-right decoder cannot do. It was trained on English Wikipedia and a large collection of books. BERT-base has 110 million parameters and BERT-large 340 million, tiny by today's standards. Facebook's RoBERTa (July 2019) showed that BERT had been undertrained and improved it with more data and longer training.

Still in daily use

Encoders are rarely in the headlines but run at huge scale: they rank web search results, flag harmful posts, route support tickets and turn documents into vectors for retrieval. Because they are small and process a passage in a single pass, they are cheap to run. ModernBERT (December 2024), from Answer.AI and LightOn, updated the design for current hardware and extended its context to 8,192 tokens.

Famous encoder models

Further reading

BuddhaBot 🇯🇵 Japan and 1 moreBuddhaBot A chatbot answering questions from early Buddhist textsDomain · Research only · 2021 BERT WorldBERT An encoder-only transformer that reads text in both directions at once.Research · Open weights · 2018 GloVe 🇺🇸 United StatesGloVe Unsupervised word embeddings from global word co-occurrence countsResearch · Fully open · 2014 MuRIL 🇮🇳 IndiaMuRIL A BERT-style encoder pre-trained on 17 Indian languages and their transliterationsEncoder · Open weights · 2021 RoBERTa 🇺🇸 United StatesRoBERTa A robustly optimised BERT pretraining study with released models and codeEncoder · Open weights · 2019 XLM-RoBERTa 🇺🇸 United StatesXLM-RoBERTa A multilingual masked language model covering 100 languages, built on RoBERTa.General · Open weights · 2019 Megatron-LM 🇺🇸 United StatesMegatron-LM Model-parallel training techniques for transformer language models with billions of parametersResearch · Fully open · 2019 BioBERT WorldBioBERT Biomedical language model based on BERT architectureDomain · Open weights · 2019 DeBERTa 🇺🇸 United StatesDeBERTa A BERT-style encoder with disentangled attention and an enhanced mask decoder.Encoder · Open weights · 2020 IndicBERT 🇮🇳 IndiaIndicBERT Multilingual encoder model for Indian languagesEncoder · Open weights · 2022 Sentence-BERT 🇩🇪 GermanySentence-BERT Efficient sentence embeddings using Siamese BERT networksEncoder · Open weights · 2019 imgNomic Embed 🇺🇸 United StatesNomic Embed Open-source long-context text embedding modelEncoder · Open weights · 2024 Jina Embeddings v3 🇩🇪 GermanyJina Embeddings v3 Multilingual text embedding model with task-specific adaptersEncoder · Open weights · 2024 DistilBERT WorldDistilBERT A smaller, faster version of the BERT language model.Encoder · Open weights · 2019 SciBERT 🇺🇸 United StatesSciBERT A BERT model trained on scientific text.Domain · Open weights · 2019 CamemBERT 🇫🇷 FranceCamemBERT French language model based on RoBERTa architectureEncoder · Open weights · 2019 ERNIE 1.0 🇨🇳 ChinaERNIE 1.0 Knowledge-enhanced language model for Chinese NLP tasks.Encoder · Research only · 2019 ELECTRA WorldELECTRA A pre-training method that trains text encoders to spot replaced tokens.Research · Research only · 2020 AfriBERTa WorldAfriBERTa Multilingual encoder model for eleven African languagesEncoder · Open weights · 2021 ModernBERT 🇺🇸 United States and 1 moreModernBERT A modernised encoder model for retrieval and classification tasks.Encoder · Open weights · 2024 Gemini Embedding 🇺🇸 United StatesGemini Embedding Google's embedding model built from Gemini for text, code and many languagesEncoder · API only · 2025 ALBERT 🇺🇸 United StatesALBERT A slimmed-down BERT encoder that shares weights across its layersEncoder · Open weights · 2019

The weekly digest

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