tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

command-r : add BPE pre-tokenization (#7063)

Browse Source 
* Add BPE pre-tokenization for Command-R/R+.

* Bump transformers convert requirement.

* command-r : add individual digits regex

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
DAN™
2024-05-05 01:19:30 -04:00
committed by GitHub
parent 6fbd432211
commit 889bdd7686
9 changed files with 168 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/CMakeLists.txt
View File

@ -83,6 +83,7 @@ llama_test(test-tokenizer-0 NAME test-tokenizer-0-bert-bge ARGS ${CMAKE
llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-gpt-2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-2.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-command-r ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-command-r.gguf)
# build test-tokenizer-1-bpe target once and add many tests
add_executable(test-tokenizer-1-bpe test-tokenizer-1-bpe.cpp)