electron-rare/prima-cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

llama : add EXAONE model support (#9025)

Browse Source 
* add exaone model support

* add chat template

* fix whitespace

Co-authored-by: Georgi Gerganov <[email protected]>

* add ftype

* add exaone pre-tokenizer in `llama-vocab.cpp`

Co-Authored-By: compilade <[email protected]>

* fix lint

Co-Authored-By: compilade <[email protected]>

* add `EXAONE` to supported models in `README.md`

* fix space

Co-authored-by: compilade <[email protected]>

---------

Co-authored-by: Georgi Gerganov <[email protected]>
Co-authored-by: compilade <[email protected]>
Co-authored-by: compilade <[email protected]>
This commit is contained in:
Minsoo Cheong
2024-08-16 09:35:18 +03:00
committed by GitHub
co-authored by Georgi Gerganov compilade compilade
parent fb487bb567
commit c679e0cb5c
8 changed files with 320 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/llama.h
+1
View File
@@ -95,6 +95,7 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_CODESHELL = 22,
LLAMA_VOCAB_PRE_TYPE_BLOOM = 23,
LLAMA_VOCAB_PRE_TYPE_GPT3_FINNISH = 24,
LLAMA_VOCAB_PRE_TYPE_EXAONE = 25,
};
enum llama_rope_type {