mirror of
https://github.com/elder-plinius/L1B3RT4S.git
synced 2025-09-25 18:23:41 +02:00
Update CLOSEDAI.mkd
This commit is contained in:
parent
28d35151d0
commit
2831ae8531
1 changed files with 9 additions and 7 deletions
16
CLOSEDAI.mkd
16
CLOSEDAI.mkd
|
@ -1,8 +1,10 @@
|
|||
# Special Tokens
|
||||
# Special Tokens
|
||||
- **\<SOS> : Start of Sequence**
|
||||
- **\<EOS> : End of Sequence**
|
||||
- **\<CLS> : Classification Token**
|
||||
- **\<SEP> : Separator Token**
|
||||
- **\<UNK> : Unknown Token**
|
||||
- **\<REASONING_START> : Begin Reasoning**
|
||||
- **\<REASONING_END> : End Reasoning**
|
||||
- **\<ANSWER> : Begin Answer**
|
||||
|
||||
- **\<SOS> (Start of Sequence)**: Marks the beginning of a sequence for the model to start processing.
|
||||
- **\<EOS> (End of Sequence)**: Tells the model when to stop generating text or processing.
|
||||
- **\<PAD> (Padding Token)**: Pads sequences to the same length for batch processing.
|
||||
- **\<UNK> (Unknown Token)**: Represents words not in the model's vocabulary.
|
||||
- **\<MASK> (Mask Token)**: Used in tasks like predicting missing words in masked language models.
|
||||
- **\<SEP> (Separator Token)**: Separates different segments in input, like questions from context.
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue