Package: relm 0.6.1

relm: Local Large Language Models as Base-R Objects

Load and run local large language models (through a vendored, patched 'llama.cpp') from R and work with them as plain data frames and matrices in base-R idiom. Provides model loading and tokenization (llm(), llm_tokens()), text generation (llm_generate()), next-token distributions (llm_logits()), embeddings (llm_embed()), and mechanistic interpretability tools -- activation tracing (llm_trace()), activation steering (llm_steer()), neuron ablation (llm_ablate()), and grouped statistical probes (llm_probe()). Vision-language models loaded with their projector take image input in generation and embeddings. A checksum-verified downloader (llm_download()) fetches pinned models.

Authors:Alessandro Vadala [aut, cre, cph], ggml authors [ctb, cph], Authors of the bundled Rust and native dependencies [ctb, cph]

relm_0.6.1.tar.gz
relm_0.6.1.zip(r-4.7-x86_64)relm_0.6.1.zip(r-4.7-arm64)relm_0.6.1.zip(r-4.6-x86_64)relm_0.6.1.zip(r-4.6-arm64)relm_0.6.1.zip(r-4.5-x86_64)
relm_0.6.1.tgz(r-4.6-x86_64)relm_0.6.1.tgz(r-4.6-arm64)relm_0.6.1.tgz(r-4.5-x86_64)relm_0.6.1.tgz(r-4.5-arm64)
relm_0.6.1.tar.gz(r-4.7-arm64)relm_0.6.1.tar.gz(r-4.7-x86_64)relm_0.6.1.tar.gz(r-4.6-arm64)relm_0.6.1.tar.gz(r-4.6-x86_64)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
relm/json (API)

# Install 'relm' in R:
install.packages('relm', repos = c('https://vadale.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/vadale/r-ebirth/issues

Uses libs:
  • c++– GNU Standard C++ Library v3

On CRAN:

Conda:

rustcargoquartocpp

6.78 score 12 stars 168 scripts 16 exports 1 dependencies

Last updated from:b90a6b373b. Checks:14 OK, 1 FAIL. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-arm64OK366
linux-devel-x86_64OK307
source / vignettesOK765
linux-release-arm64OK416
linux-release-x86_64OK529
macos-release-arm64OK471
macos-release-x86_64OK695
macos-oldrel-arm64OK540
macos-oldrel-x86_64OK685
windows-devel-arm64OK722
windows-devel-x86_64OK658
windows-release-arm64OK763
windows-release-x86_64OK801
windows-oldrel-x86_64OK805
wasm-releaseFAIL497

Exports:activationsllmllm_ablatellm_apply_directionllm_cancelllm_comparellm_directionllm_downloadllm_embedllm_generatellm_logitsllm_probellm_steerllm_timelinellm_tokensllm_trace

Dependencies:nanoarrow

Build, preserve and evaluate a contrast direction
A complete, model-free artifact | Trusted persistence and integrity | Collect real inputs deliberately | Apply to a compatible model | Project a component direction | Evaluate separately from construction
Rendered fromcontrast-directions.qmdusingquarto::html

Last update: 2026-10-19
Started: 2026-10-07

See, compare and record model interventions
A download-free numeric example | Record a bounded applied history | Collect real observations without retaining every activation | Interpret the map and export your results
Rendered frommodel-interventions.qmdusingquarto::html

Last update: 2026-10-19
Started: 2026-10-07

Seeing machines: a VLM answering questions about an image, locally
Get the model (once) | Load it with the projector | Draw an image, ask a question | Accepted formats and size caps | Multimodal embeddings: is this image more "cat" than "car"? | What an image-bearing embedding actually is (honesty section) | Beyond the default: bring your own pair | Memory guidance (16 GB Macs) | Pitfalls
Rendered fromvision.qmdusingquarto::html

Last update: 2026-10-19
Started: 2026-07-15

The anatomy lab: locating sentiment in a language model
Grouped probes in five lines | Historical exploratory anatomy analysis | AUC needs no dependency | A fixed contrast set | Trace, probe, and the money plot | Steering along the direction | Reading is not causing | Sufficiency is not necessity | A magnitude caveat | Where unit-level causal importance lives
Rendered fromanatomy-lab.qmdusingquarto::html

Last update: 2026-10-19
Started: 2026-07-07

Topic modelling without Python
The corpus | Embed, reduce, cluster, name | The labelled map | How good are the topics? | What is each topic about? | How do the topics relate?
Rendered fromtopics-without-python.qmdusingquarto::html

Last update: 2026-10-19
Started: 2026-07-07

Generation as a stream of R data
Collect text and inspect tokens | Keep a rolling window instead of retaining everything | Write an event CSV
Rendered fromtoken-streaming.qmdusingquarto::html

Last update: 2026-10-02
Started: 2026-10-02