meta-llama/llama-models

How meta-llama/llama-models works

This repository distributes Llama model assets and provides a CLI for cataloguing, downloading, verifying, and removing them, plus native Llama 3 and Llama 4 inference code. The main usage paths are CLI request → model catalog/download → local checkpoint, and prompt → model-specific inference entry point → generated text. Llama 4 also includes image preprocessing and vision components; quantization is an optional inference path. The README documents these capabilities; sampled source confirms selected implementations, so unsampled wiring is left unspecified.

Main entry points: cli Model CLI Commands · generation.py Llama 3 Generation · checkpoint.py Local Checkpoints · download.py Download Command

Components 25

Model CLI

CLI Router models/cli/llama.py
Download Command models/cli/download.py
Verify Download models/cli/verify_download.py
Remove Model models/cli/remove.py
Describe Model models/cli/describe.py
Prompt Format models/cli/prompt_format.py
Model CLI Commands models/cli

Model Assets

Model Catalog models/sku_list.py
Local Checkpoints models/checkpoint.py

Llama 3 Runtime

Llama 3 Scripts models/llama3/scripts
Llama 3 Generation models/llama3/generation.py
Chat Formatting models/llama3/chat_format.py
Llama 3 Tokenizer models/llama3/tokenizer.py
Llama 3 Model models/llama3/model.py

Llama 4 Runtime

Llama 4 Scripts models/llama4/scripts
Llama 4 Generation models/llama4/generation.py
Llama 4 Model models/llama4/model.py
Image Preprocessing models/llama4/preprocess.py
Vision Encoder models/llama4/vision/encoder.py
Vision Embeddings models/llama4/vision/embedding.py

Quantization

Llama 3 Quantization models/llama3/quantization/loader.py
Llama 4 Quantization models/llama4/quantization/loader.py
Quantization Kernels models/quantize_impls.py

Other components

Developer
Meta / Hugging Face

Connections 29

Developer → CLI Router: runs commands
CLI Router → Model CLI Commands: dispatches
Model CLI Commands → Model Catalog: lists models
Model CLI Commands → Describe Model: dispatches
Model CLI Commands → Download Command: dispatches
Model CLI Commands → Verify Download: dispatches
Model CLI Commands → Remove Model: dispatches
Model CLI Commands → Prompt Format: dispatches
Download Command → Model Catalog: selects model
Download Command → Meta / Hugging Face: downloads from
Download Command → Local Checkpoints: writes files
Verify Download → Local Checkpoints: checks files
Remove Model → Local Checkpoints: removes files
Developer → Llama 3 Scripts: runs inference
Llama 3 Scripts → Llama 3 Generation: invokes
Llama 3 Generation → Chat Formatting: formats chat
Llama 3 Generation → Llama 3 Tokenizer: tokenizes prompts
Llama 3 Generation → Llama 3 Model: runs model
Llama 3 Generation → Local Checkpoints: loads weights
Llama 3 Generation → Llama 3 Quantization: converts weights
Developer → Llama 4 Scripts: runs inference
Llama 4 Scripts → Llama 4 Generation: invokes
Llama 4 Generation → Llama 4 Model: runs model
Llama 4 Generation → Local Checkpoints: loads weights
Llama 4 Generation → Llama 4 Quantization: converts weights
Llama 3 Quantization → Quantization Kernels: uses kernels
Llama 4 Quantization → Quantization Kernels: uses kernels
Image Preprocessing → Vision Embeddings: prepares image input
Vision Embeddings → Vision Encoder: encodes patches

More Python diagrams: internlm/lmdeploy · zilliztech/deep-searcher · nvlabs/spade · jefferyhcool/bilinote · pygithub/pygithub

Drawn by GitDiagram on September 29, 2026 from the repository's file tree, README and source files. Read as Markdown ·