py : add Phi-1.5/Phi-2 tokenizer (#9361)

* add phi2 tokenizer

* add phi name to convert_hf_to_gguf_update.py

* make tokenizer_pre consistent; llama.cpp work
This commit is contained in:
daminho 2024-09-12 20:28:20 +09:00 committed by GitHub
parent 3c26a1644d
commit c837981bba
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 4 additions and 0 deletions

View File

@ -626,6 +626,9 @@ class Model:
if chkhsh == "4e2b24cc4770243d65a2c9ec19770a72f08cffc161adbb73fcbb6b7dd45a0aae":
# ref: https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct
res = "exaone"
if chkhsh == "fcace8b9cac38ce847670c970cd5892031a753a1ef381abd1d9af00f713da085":
# ref: https://huggingface.co/microsoft/phi-2
res = "phi-2"
if res is None:
logger.warning("\n")

View File

@ -98,6 +98,7 @@ models = [
{'name': "bloom", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/bigscience/bloom", },
{'name': "gpt3-finnish", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/TurkuNLP/gpt3-finnish-small", },
{"name": "exaone", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct", },
{"name": "phi-2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/microsoft/phi-2", },
]