llama3
LLama3 model family to canonical string parser
Attributes
tokens
module-attribute
tokens = (
"BOS",
"EOS",
"STARTHEADER",
"ROLE",
"MESSAGE",
"ENDHEADER",
"ENDCONTENT",
"NEWLINE",
"WHITESPACE",
)
Classes
Llama3
Bases: BaseCanonical
Llama3 lexer implementation
There is an open discussion on HF I started to clarify how the names and fewshot encoding examples need to me encoded in the Llama3 chat template: https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct/discussions/89