Relm – local LLMs as base-R objects, with interpretability

Comments

R-ebirth aims to make R a first-class environment for scientific research on data and AI - mechanistic interpretability ("AI neuroscience"), machine learning including topic modelling, and the life sciences - while staying simple for researchers.

It is delivered as relm: an R package with a Rust native core that embeds a patched llama.cpp, exposing local LLMs (loading, generation, embeddings, activation tracing, steering, and ablation) as base-R-idiom functions returning plain data.frames and matrixes.

Topic modelling with no Python: llm_embed() → UMAP → HDBSCAN → the model names each cluster. One of two runnable demos - see the package README.

Using the package? Start with the package README (quickstart, examples, the two demos) and docs/getting-started.md (install options - binaries or from source - a first run, and troubleshooting). This page is the repository/developer overview. The first public release is here.

Features

relm loads local GGUF models and exposes, as base-R objects:

• llm() model loading
• llm_tokens() tokenization
• llm_generate() text generation
• llm_logits() next-token distributions
• llm_embed() text embeddings
• llm_trace() activation tracing
• llm_steer() steering
• llm_ablate() ablation - the mechanistic-interpretability core
• llm_download() checksum-verified fetch of pinned models

Every numerical feature is validated value-for-value against an independent reference (harness B).

Vision (image inputs) is the next release (v0.2.0); v0.1.0 is text-only. The full plan is in ROADMAP.md.

Repository Structure

• rebirth/ the R package (R/, src/ + src/rust/ extendr crate, tests/, vignettes/)
• rust/ Cargo workspace: rebirth-ffi (R Rust boundary), rebirth-llm (engine)
• rebirth/src/llama.cpp/ pinned, patched llama.cpp (vendored; see its VENDORING.md)
• tests/llm-golden/ Harness B numerical goldens
• tests/demos/ the two reference demos (anatomy lab; topics without Python)
• CLAUDE.md, SOLO-PHASE-PLAN.md, ROADMAP.md, API-GRAMMAR.md, ARCHITECTURE.md, DECISIONS.md, and THESIS-PLAN.md

If anything else disagrees with these files, the files win.

Installation

End users install prebuilt binaries from r-universe (no toolchain required).

Building from source requires:

• R (>= 4.5)
• A C toolchain
• A Rust toolchain (rustup; the pinned channel is in rust-toolchain.toml)
• CMake (>= 3.28) for the vendored engine

# native workspace
cd rust && cargo test && cargo clippy --all-targets -- -D warnings

# R package
R CMD build rebirth && R CMD check relm_0.1.0.tar.gz

License

Dual-licensed MIT OR Apache-2.0 - see LICENSE.md. The vendored llama.cpp is MIT (see NOTICE). The name is protected: modified redistributions must rename (see TRADEMARK.md).