Package: relm 0.1.0

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'), text embeddings ('llm_embed'), and mechanistic interpretability tools -- activation tracing ('llm_trace'), activation steering ('llm_steer'), and neuron ablation ('llm_ablate'). A checksum-verified downloader ('llm_download') fetches pinned models.

Authors:Alessandro Vadala [aut, cre, cph]

relm_0.1.0.tar.gz

relm_0.1.0.tgz(r-4.6-x86_64)relm_0.1.0.tgz(r-4.6-arm64)relm_0.1.0.tgz(r-4.5-x86_64)relm_0.1.0.tgz(r-4.5-arm64)
relm_0.1.0.tar.gz(r-4.7-arm64)relm_0.1.0.tar.gz(r-4.7-x86_64)relm_0.1.0.tar.gz(r-4.6-arm64)relm_0.1.0.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

3.30 score 1 stars 8 scripts 9 exports 1 dependencies

Last updated from:a50502b396. Checks:8 NOTE, 1 OK, 4 FAIL. Indexed: yes.

TargetResultTimeFilesSyslog
linux-devel-arm64NOTE361
linux-devel-x86_64NOTE384
source / vignettesOK680
linux-release-arm64NOTE348
linux-release-x86_64NOTE379
macos-release-arm64NOTE388
macos-release-x86_64NOTE626
macos-oldrel-arm64NOTE409
macos-oldrel-x86_64NOTE783
windows-develFAIL196
windows-releaseFAIL158
windows-oldrelFAIL178
wasm-releaseFAIL188

Exports:llmllm_ablatellm_downloadllm_embedllm_generatellm_logitsllm_steerllm_tokensllm_trace

Dependencies:nanoarrow

The anatomy lab: locating sentiment in a language model
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

Last update: 2026-07-08
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?

Last update: 2026-07-08
Started: 2026-07-07