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

convert : add "tokenizer.ggml.pre" GGUF KV (wip)

Browse source
This commit is contained in:
Georgi Gerganov 2024-04-26 19:21:55 +03:00
parent e3f6dc7409
commit 9b4d63ae53
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
6 changed files with 58 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

2
gguf-py/gguf/constants.py
View file

@ -72,6 +72,7 @@ class Keys:
class Tokenizer:
MODEL = "tokenizer.ggml.model"
PRE = "tokenizer.ggml.pre"
LIST = "tokenizer.ggml.tokens"
TOKEN_TYPE = "tokenizer.ggml.token_type"
TOKEN_TYPE_COUNT = "tokenizer.ggml.token_type_count" # for BERT-style token types
@ -940,6 +941,7 @@ KEY_SSM_TIME_STEP_RANK = Keys.SSM.TIME_STEP_RANK
# tokenization
KEY_TOKENIZER_MODEL = Keys.Tokenizer.MODEL
KEY_TOKENIZER_PRE = Keys.Tokenizer.PRE
KEY_TOKENIZER_LIST = Keys.Tokenizer.LIST
KEY_TOKENIZER_TOKEN_TYPE = Keys.Tokenizer.TOKEN_TYPE
KEY_TOKENIZER_SCORES = Keys.Tokenizer.SCORES