architecture-catalog.json
artificial-intelligence/large-language-models/models/architecture-catalog.json · 249 line(s) · json
{
"schema_version": "1.0",
"title": "Language model architecture and system taxonomy",
"scope": "Representative families known through 2025, with a separate speculative placeholder for 2026โ2500.",
"warning": "This is a curated taxonomy, not a count of 2,000โ2,500 distinct models and not an exhaustive catalogue of products or checkpoints.",
"entries": [
{
"id": "n-gram",
"name": "Statistical language model",
"description": "Predicts tokens from local frequency context; useful baseline, limited long-range structure.",
"period_or_status": "2000s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "hidden-markov-model",
"name": "Probabilistic sequence model",
"description": "Models hidden states and observed token sequences; historically important for speech and NLP.",
"period_or_status": "pre-2010",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "conditional-random-field",
"name": "Structured prediction",
"description": "Labels sequences using contextual feature dependencies in classical NLP pipelines.",
"period_or_status": "2000s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "feed-forward-neural-lm",
"name": "Neural language model",
"description": "Predicts a token from a fixed context window using dense neural layers.",
"period_or_status": "2000s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "rnn",
"name": "Recurrent neural network",
"description": "Processes sequences with recurrent state; foundational neural sequence architecture.",
"period_or_status": "2010s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "lstm",
"name": "Gated recurrent network",
"description": "Uses input, forget, and output gates to retain information over longer sequences.",
"period_or_status": "2010s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "gru",
"name": "Gated recurrent network",
"description": "A streamlined gated recurrent architecture with update and reset gates.",
"period_or_status": "2010s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "seq2seq",
"name": "Encoder-decoder sequence model",
"description": "Maps an input sequence to an output sequence, often with recurrent or transformer components.",
"period_or_status": "2010s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "attention-seq2seq",
"name": "Attention-based encoder-decoder",
"description": "Allows decoder steps to focus on relevant encoded input positions.",
"period_or_status": "2010s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "transformer-encoder",
"name": "Bidirectional encoder",
"description": "Uses self-attention and feed-forward blocks for contextual representations; BERT-style family.",
"period_or_status": "2018 onward",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "transformer-decoder",
"name": "Autoregressive decoder",
"description": "Uses causal self-attention to predict the next token; GPT-style family.",
"period_or_status": "2018 onward",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "encoder-decoder-transformer",
"name": "Text-to-text transformer",
"description": "Uses an encoder and autoregressive decoder for translation, summarization, and general text tasks.",
"period_or_status": "2019 onward",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "sparse-mixture-of-experts",
"name": "Conditional-compute model",
"description": "Routes tokens or examples to a subset of expert networks to scale capacity with conditional computation.",
"period_or_status": "2020s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "retrieval-augmented-generation",
"name": "Retrieval-grounded model system",
"description": "Combines a language model with search or document retrieval; retrieved evidence is distinct from model weights.",
"period_or_status": "2020s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "long-context-transformer",
"name": "Extended-context model",
"description": "Uses attention variants, memory, or position strategies to process longer sequences.",
"period_or_status": "2020s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "state-space-language-model",
"name": "State-space sequence model",
"description": "Uses structured state-space dynamics or selective scans as an alternative to full attention in some settings.",
"period_or_status": "2020s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "hybrid-attention-state-space",
"name": "Hybrid sequence model",
"description": "Combines attention layers with state-space or recurrent components.",
"period_or_status": "2020s",
"evidence_status": "emerging",
"category": "architecture-or-system-pattern"
},
{
"id": "multimodal-language-model",
"name": "Multimodal model",
"description": "Connects text with image, audio, video, or other modality encoders and decoders.",
"period_or_status": "2020s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "speech-language-model",
"name": "Audio/speech model",
"description": "Processes or generates speech/audio, sometimes through discrete audio tokens or aligned encoders.",
"period_or_status": "2020s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "code-language-model",
"name": "Code-specialized model",
"description": "Trains on source code and text for completion, explanation, transformation, and tool-assisted coding.",
"period_or_status": "2020s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "vision-language-model",
"name": "Vision-text model",
"description": "Aligns visual representations with language for image understanding and visual question answering.",
"period_or_status": "2020s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "diffusion-language-hybrid",
"name": "Generative hybrid",
"description": "Combines language modeling with diffusion-style generation or refinement; implementations vary.",
"period_or_status": "2020s",
"evidence_status": "research",
"category": "architecture-or-system-pattern"
},
{
"id": "agentic-model-system",
"name": "Tool-using model system",
"description": "Combines an LLM with planning, tools, memory, and feedback loops; system design rather than a single neural architecture.",
"period_or_status": "2020s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "continual-learning-model",
"name": "Continual adaptation system",
"description": "Updates or adapts from sequential data while attempting to limit catastrophic forgetting.",
"period_or_status": "ongoing",
"evidence_status": "research",
"category": "architecture-or-system-pattern"
},
{
"id": "neuromorphic-language-model",
"name": "Brain-inspired computing model",
"description": "Explores spiking or event-driven computation for language-related workloads.",
"period_or_status": "ongoing",
"evidence_status": "research",
"category": "architecture-or-system-pattern"
},
{
"id": "quantized-language-model",
"name": "Compressed deployment variant",
"description": "Uses reduced-precision weights or activations to lower memory and compute; orthogonal to base architecture.",
"period_or_status": "2020s",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "distilled-language-model",
"name": "Compressed student model",
"description": "Transfers behavior from a larger teacher to a smaller model; orthogonal to base architecture.",
"period_or_status": "2010s onward",
"evidence_status": "established",
"category": "architecture-or-system-pattern"
},
{
"id": "federated-language-model",
"name": "Distributed training system",
"description": "Trains across decentralized data holders with aggregation and privacy constraints; a training topology, not an architecture.",
"period_or_status": "2020s",
"evidence_status": "research",
"category": "architecture-or-system-pattern"
},
{
"id": "neuro-symbolic-language-system",
"name": "Hybrid symbolic-neural system",
"description": "Combines neural language processing with explicit rules, logic, knowledge graphs, or verifiers.",
"period_or_status": "ongoing",
"evidence_status": "research",
"category": "architecture-or-system-pattern"
},
{
"id": "future-hypothetical-model",
"name": "Speculative category",
"description": "Potential post-2025 systems through 2500 cannot be catalogued as known facts; record proposals separately with evidence and uncertainty.",
"period_or_status": "2026โ2500",
"evidence_status": "speculative",
"category": "architecture-or-system-pattern"
}
]
}