py : support converting local models (#7547)

* Support of converting local models added to convert-hf-to-gguf-update.py

* Description fixed

* shutil added to imports
This commit is contained in:
Pavel Zloi 2024-09-11 15:29:51 +03:00 committed by GitHub
parent 0996c5597f
commit 8db003a19d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -31,6 +31,7 @@ import re
import requests import requests
import sys import sys
import json import json
import shutil
from hashlib import sha256 from hashlib import sha256
from enum import IntEnum, auto from enum import IntEnum, auto
@ -125,12 +126,27 @@ def download_model(model):
if tokt == TOKENIZER_TYPE.UGM: if tokt == TOKENIZER_TYPE.UGM:
files.append("spiece.model") files.append("spiece.model")
for file in files: if os.path.isdir(repo):
save_path = f"models/tokenizers/{name}/{file}" # If repo is a path on the file system, copy the directory
if os.path.isfile(save_path): for file in files:
logger.info(f"{name}: File {save_path} already exists - skipping") src_path = os.path.join(repo, file)
continue dst_path = f"models/tokenizers/{name}/{file}"
download_file_with_auth(f"{repo}/resolve/main/{file}", token, save_path) if os.path.isfile(dst_path):
logger.info(f"{name}: File {dst_path} already exists - skipping")
continue
if os.path.isfile(src_path):
shutil.copy2(src_path, dst_path)
logger.info(f"{name}: Copied {src_path} to {dst_path}")
else:
logger.warning(f"{name}: Source file {src_path} does not exist")
else:
# If repo is a URL, download the files
for file in files:
save_path = f"models/tokenizers/{name}/{file}"
if os.path.isfile(save_path):
logger.info(f"{name}: File {save_path} already exists - skipping")
continue
download_file_with_auth(f"{repo}/resolve/main/{file}", token, save_path)
for model in models: for model in models: