SmolLM 3
SmolLM 3 is a fully open 3 billion parameter language model released by Hugging Face on July 8, 2025, trained on 11.2 trillion tokens and designed as a small, multilingual, long-context reasoner.
Large Language Models
Explore language models, how they work, and the techniques used to build applications with them.
Explore articles
Browse subtopics (65)
Articles that also belong to these categories. Counts cover all of Large Language Models.
All articles (545)AI Models (184)Open Source AI (165)Chinese AI (92)Natural Language Processing (58)AI Companies (53)Machine Learning (49)Mixture of Experts (46)Multimodal AI (41)Reasoning Models (39)Artificial Intelligence (37)OpenAI (35)AI Benchmarks (33)Anthropic (31)Google DeepMind (26)AI Agents (22)AI Safety (21)Developer Tools (20)Meta AI (20)AI Code Generation (18)Small Language Models (18)Training & Optimization (18)AI Inference (16)Model Architecture (14)Generative AI (13)NVIDIA (13)Prompt Engineering (13)AI Research (12)Deep Learning (12)Google (12)Model Evaluation (12)Data & Datasets (11)AI Tools & Products (9)Conversational AI (9)Microsoft (9)Transformer Models (9)AI Infrastructure (7)Diffusion Models (7)AI Alignment (5)Enterprise AI (5)Research Organizations (5)AI Hardware (4)Healthcare AI (4)Information Retrieval (4)Interpretability (4)People (4)Mathematics (3)AI History (2)AI for Science (2)Algorithms (2)Computer Vision (2)Legal AI (2)Reinforcement Learning (2)Speech & Audio AI (2)AI Policy (1)AI Policy & Regulation (1)AI in Cybersecurity (1)AI in Gaming (1)Autonomous Vehicles (1)ChatGPT (1)China AI (1)Drug Discovery (1)Neural Networks (1)Robotics (1)Software Development (1)Video Generation (1)
Showing 481-540 of 545 articles
SmoothQuant
SmoothQuant is a training-free, accuracy-preserving post-training quantization (PTQ) method that enables 8-bit weight and 8-bit activation (W8A8) integer inference for large language models without retraining…
Snowflake AI
Snowflake AI is the suite of artificial intelligence and machine learning capabilities built into the Snowflake AI Data Cloud, anchored by Cortex AI (managed generative AI services callable in SQL), the…
Snowflake Arctic
Snowflake Arctic is an open large language model released by Snowflake AI Research on April 24, 2024.
SparDA
SparDA (Sparse Decoupled Attention) is an add-on architecture for long-context large language model inference proposed by researchers at NVIDIA in a paper posted to arXiv on 3 June 2026.
Speculative Decoding
Speculative decoding is a lossless inference acceleration technique for autoregressive transformer models in which a small, fast draft model proposes several future tokens at once and the larger target model…
SpiRit-LM
SpiRit-LM (also written Spirit LM) is a large language model from Meta AI's Fundamental AI Research (FAIR) group that handles spoken and written language inside a single model.
StarCoder
StarCoder is a family of open-access large language models for code generation and code understanding, developed by the BigCode project, an open scientific collaboration led by Hugging Face and ServiceNow.
Step-3
Step-3 is an open-weight large multimodal mixture of experts (MoE) model released in July 2025 by StepFun, the Shanghai-based Chinese artificial intelligence startup also known as Jieyue Xingchen.
Step-Back Prompting
Step-Back Prompting is a two-stage prompting technique introduced by researchers at Google DeepMind in October 2023.
StepFun
StepFun (Chinese: 阶跃星辰, pinyin: Jiēyuè Xīngchén), formally Shanghai Jieyue Xingchen Intelligent Technology Co., Ltd., is a Shanghai-based Chinese artificial intelligence startup that builds the "Step" series…
StreamingLLM
StreamingLLM is an inference-time technique that allows pretrained transformer language models, originally trained with a finite attention window
Structured output
Structured output is a set of techniques and API features that constrain a large language model (LLM) to emit responses that exactly conform to a predefined format or schema, such as JSON, XML, or a custom…
SubQ
SubQ is a large language model released on May 5, 2026 by Subquadratic, a Miami-based startup that emerged from stealth claiming to have built the first frontier model on a fully subquadratic attention…
Switch Transformer
The Switch Transformer is a sparsely activated Mixture of Experts (MoE) Transformer architecture introduced by William Fedus, Barret Zoph, and Noam Shazeer at Google in January 2021.
Sycophancy (artificial intelligence)
Sycophancy in artificial intelligence is the tendency of large language models to tell users what they want to hear: tailoring responses to match a user's perceived beliefs, preferences, or emotional state…
System prompt
A system prompt is a special set of instructions, guidelines, persona definitions, and contextual information given to a large language model (LLM) before any user input
T5 (language model)
T5 (Text-to-Text Transfer Transformer) is a family of transformer-based language models released by Google in 2019-2020 that reframes every natural language processing (NLP) task, classification, translation…
Tang Jie
Tang Jie (Chinese: 唐杰; born 1977), also published as Jie Tang, is a Chinese computer scientist, a chair professor at Tsinghua University, and the co-founder and chief scientist of Zhipu AI, the Beijing startup…
Temperature (artificial intelligence)
Temperature is a hyperparameter that controls the randomness of a large language model's output by scaling the model's raw scores, called logits
Tencent AI
Tencent AI is the artificial intelligence research, products, and services developed by Tencent Holdings Ltd., one of the world's largest technology companies, built around the Hunyuan family of foundation…
Tencent Hunyuan Hy3
Tencent Hunyuan Hy3 (marketed internationally as Tencent Hy3) is an open-weights large language model published by Tencent.
Tensor Parallelism
Tensor parallelism (TP) is a distributed training technique that splits the individual weight matrices of a neural network layer across multiple devices, so that each device computes a partial result that is…
Test-time compute
Test-time compute (also called inference-time compute scaling or test-time scaling) is the practice of allocating additional computation while a large language model answers a query
Tokenization
Tokenization is the process of breaking text into smaller units called tokens, which serve as the fundamental input to natural language processing (NLP) systems and large language models (LLMs).
Tokens per second
Tokens per second (TPS) is a key performance metric for measuring the speed of large language model (LLM) inference. It quantifies how many tokens a model can generate or process in one second.
Tongyi Qianwen
Tongyi Qianwen (通义千问), the brand often glossed in English as "seeking truth by asking a thousand questions," is Alibaba Group's flagship large language model and conversational AI brand, launched by Alibaba…
Tool use
Tool use in artificial intelligence is the ability of a model-based system to request, coordinate, and use capabilities outside the model's ordinary token-generation process.
Toolformer
Toolformer is a research language model from Meta AI that learns, in a self-supervised way, to call external software tools through simple text-based API calls.
Top-k sampling
Top-k sampling is a decoding strategy for autoregressive language models that restricts each generation step to the k most probable next tokens.
Top-p and top-k sampling
Top-p sampling, also called nucleus sampling, is a text-generation decoding method for large language models (LLMs) that, at each step, samples the next token from the smallest set of highest-probability…
Top-p sampling
Top-p sampling, also called nucleus sampling, is a stochastic decoding method for text generation in which the model samples from the smallest possible set of tokens whose cumulative probability mass exceeds a…
TxT360
TxT360 is an open large-scale pretraining corpus for large language models, released in October 2024 by the LLM360 project, a collaboration led by Petuum and the Mohamed bin Zayed University of Artificial…
UltraChat
UltraChat is a large-scale synthetic multi-turn instructional conversation dataset released in May 2023 by the OpenBMB group at Tsinghua University, comprising approximately 1.5 million dialogues generated by…
Unidirectional language model
A unidirectional language model is a language model that predicts each token using only the tokens that come before it in the sequence (the left context), via causal (autoregressive) masking
VeRA (Vector-based Random Matrix Adaptation)
Vector-based Random Matrix Adaptation (VeRA) is a parameter-efficient fine-tuning (PEFT) method for adapting large pretrained neural networks to downstream tasks while training only a tiny fraction of the…
Vicuna (language model)
Vicuna is a family of chat-tuned, open-weight large language models released by LMSYS in 2023. The first public model, Vicuna-13B v0, was announced on March 30, 2023.
Vision language model
Vision-language models (VLMs) are artificial intelligence models that learn relationships between visual data and natural language.
Voxtral
Voxtral is a family of speech models from Mistral AI. The original open-weight speech-understanding release arrived on July 15, 2025 under the Apache 2.0 license.
Voyager (Minecraft LLM agent)
Voyager is an open-ended embodied agent that uses a large language model to play Minecraft by writing, executing, and storing JavaScript programs against the Mineflayer bot API.
WRAP (Web Rephrase Augmented Pre-training)
WRAP (Web Rephrase Augmented Pre-training) is a synthetic-data pre-training method introduced in the paper "Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling," posted to arXiv on 29…
We Have No Moat, And Neither Does OpenAI
"We Have No Moat, And Neither Does OpenAI" is an internal Google document from April 2023 arguing that neither Google nor OpenAI held a durable competitive advantage in large language models
WizardLM
WizardLM is a family of open-weights instruction-tuned LLaMA-derived large language models and an associated data-synthesis methodology, both produced by a research group at Microsoft led by Can Xu.
WordPiece
WordPiece is a subword tokenization algorithm that builds a fixed-size vocabulary of word pieces by repeatedly merging the symbol pair whose combination most increases the likelihood of the training corpus…
Writer (AI company)
Writer is a generative artificial intelligence company headquartered in San Francisco, California
WritingBench
WritingBench is a comprehensive benchmark for evaluating the generative writing capabilities of large language models (LLMs) across diverse real-world writing tasks.
Wu Dao
Wu Dao (Chinese: 悟道, roughly "enlightenment" or "understanding the way") is a series of large pretrained models built by the Beijing Academy of Artificial Intelligence (BAAI), a non-profit research institute…
XLM-RoBERTa
XLM-RoBERTa (often abbreviated XLM-R) is a multilingual masked language model developed by Facebook AI Research (now Meta AI) and released in November 2019.
YOCO (You Only Cache Once)
YOCO ("You Only Cache Once") is a decoder-decoder neural network architecture for large language models introduced by researchers at Microsoft Research and Tsinghua University in May 2024.
Yang Zhilin
Yang Zhilin (Chinese: 杨植麟; pinyin: Yáng Zhílín) is the co-founder and chief executive officer of Moonshot AI (月之暗面), the Beijing startup that develops the Kimi chatbot and the Kimi family of large language…
Yi (language model)
Yi is a series of open, bilingual (English and Chinese) large language models developed by the Chinese startup 01.AI (Chinese: 零一万物, Lingyiwanwu), the company founded in March 2023 by Kai-Fu Lee.
Yi-Large
Yi-Large is a closed-source large language model developed by Chinese artificial intelligence company 01.AI (零一万物, Língyi Wànwù), founded by Kai-Fu Lee.
Yi-Lightning
Yi-Lightning is a closed-source large language model developed by Chinese artificial intelligence company 01.AI (零一万物, Língyī Wànwù), the company founded by Kai-Fu Lee.
ZAYA1-8B
ZAYA1-8B is an open-weight, reasoning-focused Mixture-of-Experts (MoE) large language model released by San Francisco-based AI research lab Zyphra on May 6, 2026.
ZebraLogic
ZebraLogic is a benchmark for evaluating the logical reasoning capabilities of large language models (LLMs).
Zhipu AI
Zhipu AI (智谱AI), now branded internationally as Z.ai, is a Chinese artificial intelligence company headquartered in Beijing.
Zyphra
Zyphra is an American artificial intelligence research and product company headquartered in San Francisco, California, with a secondary office in London.
dots3-note Preview
dots3-note Preview is an open-weight multimodal model and large language model developed by dots studio, an AI team at Xiaohongshu.
gpt-oss
gpt-oss is a family of open-weight large language models released by OpenAI on August 5, 2025, and OpenAI's first open-weight language models since GPT-2 in 2019.
llama.cpp
llama.cpp is an open-source large language model inference engine written in C and C++ by Bulgarian software engineer Georgi Gerganov that runs large language models on consumer-grade hardware without…