Package: Rlimite 0.1.0
Rlimite: Native 'torch' Inference for Limite Mathematical Language Models
Implements the Limite mathematical language-model architecture <https://github.com/paradigma-inc/limite-violetto> directly with 'torch'. Loads the published Base, Base Soup, and Violetto 'safetensors' checkpoints and tokenizers from the 'Hugging Face' Hub without a Python runtime or model-serving process. Provides cached autoregressive generation and the official single-turn prompt format used by the math-specialized Violetto checkpoint.
Authors:
Rlimite_0.1.0.tar.gz
Rlimite_0.1.0.zip(r-4.7-any)Rlimite_0.1.0.zip(r-4.6-any)Rlimite_0.1.0.zip(r-4.5-any)
Rlimite_0.1.0.tgz(r-4.6-any)Rlimite_0.1.0.tgz(r-4.5-any)
Rlimite_0.1.0.tar.gz(r-4.7-any)Rlimite_0.1.0.tar.gz(r-4.6-any)
Rlimite_0.1.0.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION |NEWS
card.svg |card.png
Rlimite/json (API)
| # Install 'Rlimite' in R: |
| install.packages('Rlimite', repos = c('https://sounkou-bioinfo.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/sounkou-bioinfo/rlimite/issues
Pkgdown/docs site:https://sounkou-bioinfo.github.io
huggingfaceinferencellmmathematicssafetensorstorch
Last updated from:dabee30405. Checks:7 ERROR, 2 OK. Indexed: yes.
| Target | Result | Time | Files | Syslog |
|---|---|---|---|---|
| linux-devel | ERROR | 166 | ||
| source / vignettes | OK | 353 | ||
| linux-release | ERROR | 122 | ||
| macos-release | ERROR | 123 | ||
| macos-oldrel | ERROR | 81 | ||
| windows-devel | ERROR | 108 | ||
| windows-release | ERROR | 84 | ||
| windows-oldrel | ERROR | 81 | ||
| wasm-release | OK | 134 |
Exports:limitelimite_chatlimite_chat_promptlimite_checkpointslimite_configlimite_from_configlimite_from_pretrainedlimite_generatelimite_state_dictlimite_tokenizer
Dependencies:askpassbitbit64callrclicorocurldescfarverfilelockfsgluehfhubhttrjsonlitelabelinglifecyclemagrittrmimeopensslotelprocessxpsR6RColorBrewerRcpprlangsafetensorsscalessystoktorchtriebeardurltoolsviridisLitewithr
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Construct a Limite language model | limite |
| Generate a Limite response | limite_chat |
| Format messages with the published Limite template | limite_chat_prompt |
| Published Limite checkpoints | limite_checkpoints |
| Limite model configuration | limite_config |
| Construct Limite from checkpoint configuration | limite_from_config |
| Load a pretrained Limite model | limite_from_pretrained |
| Generate tokens with a Limite model | limite_generate |
| Load a Limite checkpoint state dictionary | limite_state_dict |
| Load the Limite tokenizer | limite_tokenizer |