tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-30 06:03:37 -04:00
Code Issues Packages Projects Releases Wiki Activity

llama : improve infill support and special token detection (#9798)

Browse Source 
* llama : improve infill support

ggml-ci

* llama : add more FIM token strings

ggml-ci

* server : update prompt on slot restore (#9800)

* gguf : deprecate old FIM token KVs
This commit is contained in:
Georgi Gerganov
2024-10-12 08:21:51 +03:00
committed by GitHub
parent 943d20b411
commit 11ac9800af
12 changed files with 601 additions and 427 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
gguf-py/gguf/gguf_writer.py
View File

@@ -843,15 +843,6 @@ class GGUFWriter:
self.add_string(Keys.Tokenizer.CHAT_TEMPLATE, value)
def add_prefix_token_id(self, id: int) -> None:
self.add_uint32(Keys.Tokenizer.PREFIX_ID, id)
def add_suffix_token_id(self, id: int) -> None:
self.add_uint32(Keys.Tokenizer.SUFFIX_ID, id)
def add_middle_token_id(self, id: int) -> None:
self.add_uint32(Keys.Tokenizer.MIDDLE_ID, id)
def add_eot_token_id(self, id: int) -> None:
self.add_uint32(Keys.Tokenizer.EOT_ID, id)