[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
02/18: gnu: Add sentencepiece.
From: |
guix-commits |
Subject: |
02/18: gnu: Add sentencepiece. |
Date: |
Sat, 8 Apr 2023 08:14:49 -0400 (EDT) |
ngz pushed a commit to branch master
in repository guix.
commit 3ede522d3dfcbd6b6f971e299e7059c5fe775ba7
Author: Nicolas Graves <ngraves@ngraves.fr>
AuthorDate: Sat Mar 25 16:32:18 2023 +0100
gnu: Add sentencepiece.
* gnu/packages/machine-learning.scm (sentencepiece): New variable.
Signed-off-by: Nicolas Goaziou <mail@nicolasgoaziou.fr>
---
gnu/packages/machine-learning.scm | 28 ++++++++++++++++++++++++++++
1 file changed, 28 insertions(+)
diff --git a/gnu/packages/machine-learning.scm
b/gnu/packages/machine-learning.scm
index 37d4ef78ad..072fb1ab15 100644
--- a/gnu/packages/machine-learning.scm
+++ b/gnu/packages/machine-learning.scm
@@ -583,6 +583,34 @@ optimizing, and searching weighted finite-state
transducers (FSTs).")
'("--enable-shared" "--enable-far" "--enable-ngram-fsts"
"--enable-lookahead-fsts" "--with-pic" "--disable-bin")))))
+(define-public sentencepiece
+ (package
+ (name "sentencepiece")
+ (version "0.1.97")
+ (source
+ (origin
+ (method git-fetch)
+ (uri (git-reference
+ (url "https://github.com/google/sentencepiece")
+ (commit (string-append "v" version))))
+ (file-name (git-file-name name version))
+ (sha256
+ (base32 "1kzfkp2pk0vabyw3wmkh16h11chzq63mzc20ddhsag5fp6s91ajg"))))
+ (build-system cmake-build-system)
+ (arguments (list #:tests? #f)) ;no tests
+ (native-inputs (list gperftools))
+ (home-page "https://github.com/google/sentencepiece")
+ (synopsis "Unsupervised tokenizer for Neural Network-based text
generation")
+ (description
+ "SentencePiece is an unsupervised text tokenizer and detokenizer mainly
+for Neural Network-based text generation systems where the vocabulary size is
+predetermined prior to the neural model training. SentencePiece implements
+subword units---e.g., byte-pair-encoding (BPE) and unigram language
+model---with the extension of direct training from raw sentences.
+SentencePiece allows us to make a purely end-to-end system that does not
+depend on language-specific pre- or post-processing.")
+ (license license:asl2.0)))
+
(define-public shogun
(package
(name "shogun")
- branch master updated (ff05a38d20 -> b08cdfc6d3), guix-commits, 2023/04/08
- 06/18: gnu: Add texlive-soulutf8., guix-commits, 2023/04/08
- 05/18: gnu: Add emacs-gptel., guix-commits, 2023/04/08
- 09/18: gnu: tuxedo-keyboard: Update to 3.2.1., guix-commits, 2023/04/08
- 02/18: gnu: Add sentencepiece.,
guix-commits <=
- 01/18: gnu: Remove abandoned spotify-tui package., guix-commits, 2023/04/08
- 12/18: gnu: darktable: Update to 4.2.1., guix-commits, 2023/04/08
- 15/18: gnu: gallery-dl: Update to 1.25.1., guix-commits, 2023/04/08
- 16/18: gnu: Add emacs-flymake-popon., guix-commits, 2023/04/08
- 17/18: gnu: emacs-ement: Update to 0.8.2., guix-commits, 2023/04/08
- 07/18: gnu: fet: Update to 6.8.7., guix-commits, 2023/04/08
- 08/18: gnu: pyzo: Update to 4.12.8., guix-commits, 2023/04/08
- 11/18: gnu: scintilla: Update to 5.3.4., guix-commits, 2023/04/08
- 14/18: gnu: ruby-pg: Update to 1.4.6., guix-commits, 2023/04/08
- 13/18: gnu: darktable: Improve package style., guix-commits, 2023/04/08