CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

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
8 changed files with 167 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
llama.h
View File

@@ -81,8 +81,9 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_GPT2 = 7,
LLAMA_VOCAB_PRE_TYPE_REFACT = 8,
LLAMA_VOCAB_PRE_TYPE_COMMAND_R = 9,
LLAMA_VOCAB_PRE_TYPE_OLMO = 10,
LLAMA_VOCAB_PRE_TYPE_DBRX = 11,
LLAMA_VOCAB_PRE_TYPE_QWEN2 = 10,
LLAMA_VOCAB_PRE_TYPE_OLMO = 11,
LLAMA_VOCAB_PRE_TYPE_DBRX = 12,
};
// note: these values should be synchronized with ggml_rope