Added support for Viking pre-tokenizer (#8135)

Co-authored-by: kustaaya <kustaaya@protonmail.com>
This commit is contained in:
kustaaya 2024-06-27 11:58:54 +03:00 committed by GitHub
parent 911e35bb8b
commit f675b20a3b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 14 additions and 0 deletions

View file

@ -487,6 +487,9 @@ class Model:
if chkhsh == "7967bfa498ade6b757b064f31e964dddbb80f8f9a4d68d4ba7998fcf281c531a":
# ref: https://huggingface.co/jinaai/jina-embeddings-v2-base-code
res = "jina-v2-code"
if chkhsh == "7fc505bd3104ca1083b150b17d088b59534ede9bde81f0dd2090967d7fe52cee":
# ref: https://huggingface.co/LumiOpen/Viking-7B
res = "viking"
if res is None:
logger.warning("\n")