llama : add BPE pre-tokenization for Qwen2 (#7114)

* Add BPE pre-tokenization for Qwen2.

* minor : fixes

---------

Co-authored-by: Ren Xuancheng <17811943+jklj077@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Ren Xuancheng 2024-05-08 20:06:43 +08:00 committed by GitHub
parent 1fd9c1741d
commit 229ffff872
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 167 additions and 2 deletions

View file

@ -314,6 +314,9 @@ class Model(ABC):
if chkhsh == "9c2227e4dd922002fb81bde4fc02b0483ca4f12911410dee2255e4987644e3f8":
# ref: https://huggingface.co/CohereForAI/c4ai-command-r-v01
res = "command-r"
if chkhsh == "e636dc30a262dcc0d8c323492e32ae2b70728f4df7dfe9737d9f920a282b8aea":
# ref: https://huggingface.co/Qwen/Qwen1.5-7B
res = "qwen2"
if chkhsh == "b6dc8df998e1cfbdc4eac8243701a65afe638679230920b50d6f17d81c098166":
# ref: https://huggingface.co/allenai/OLMo-1.7-7B-hf
res = "olmo"