vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : add BPE pre-tokenization for Qwen2 (#7114)

Browse source 
* Add BPE pre-tokenization for Qwen2.

* minor : fixes

---------

Co-authored-by: Ren Xuancheng <17811943+jklj077@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Ren Xuancheng 2024-05-08 20:06:43 +08:00 • committed by GitHub
parent 1fd9c1741d
commit 229ffff872
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 167 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

1
tests/CMakeLists.txt
View file

@ -84,6 +84,7 @@ llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder ARGS ${CMAKE
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)
llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-qwen2.gguf)
# build test-tokenizer-1-bpe target once and add many tests
add_executable(test-tokenizer-1-bpe test-tokenizer-1-bpe.cpp)