vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

*.py: Stylistic adjustments for python (#8233)

Browse source 
* Superflous parens in conditionals were removed.
* Unused args in function were removed.
* Replaced unused `idx` var with `_`
* Initializing file_format and format_version attributes
* Renaming constant to capitals
* Preventing redefinition of the `f` var

Signed-off-by: Jiri Podivin <jpodivin@redhat.com>
This commit is contained in:
Jiří Podivín 2024-07-22 15:44:53 +02:00 • committed by GitHub
parent 6f11a83e4e
commit 566daa5a5b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 17 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

12
convert_hf_to_gguf_update.py
View file

@ -50,7 +50,7 @@ class TOKENIZER_TYPE(IntEnum):
# TODO: this string has to exercise as much pre-tokenizer functionality as possible
# will be updated with time - contributions welcome
chktxt = '\n \n\n \n\n\n \t \t\t \t\n \n \n \n \n🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ 🦙🦙 3 33 333 3333 33333 333333 3333333 33333333 3.3 3..3 3...3 កាន់តែពិសេសអាច😁 ?我想在apple工作1314151天～ ------======= нещо на Български \'\'\'\'\'\'```````\"\"\"\"......!!!!!!?????? I\'ve been \'told he\'s there, \'RE you sure? \'M not sure I\'ll make it, \'D you like some tea? We\'Ve a\'lL'
CHK_TXT = '\n \n\n \n\n\n \t \t\t \t\n \n \n \n \n🚀 (normal) 😶‍🌫️ (multiple emojis concatenated) ✅ 🦙🦙 3 33 333 3333 33333 333333 3333333 33333333 3.3 3..3 3...3 កាន់តែពិសេសអាច😁 ?我想在apple工作1314151天～ ------======= нещо на Български \'\'\'\'\'\'```````\"\"\"\"......!!!!!!?????? I\'ve been \'told he\'s there, \'RE you sure? \'M not sure I\'ll make it, \'D you like some tea? We\'Ve a\'lL'
if len(sys.argv) == 2:
token = sys.argv[1]
@ -100,8 +100,8 @@ def download_file_with_auth(url, token, save_path):
response = sess.get(url, headers=headers)
response.raise_for_status()
os.makedirs(os.path.dirname(save_path), exist_ok=True)
with open(save_path, 'wb') as f:
f.write(response.content)
with open(save_path, 'wb') as downloaded_file:
downloaded_file.write(response.content)
logger.info(f"File {save_path} downloaded successfully")
@ -160,7 +160,7 @@ for model in models:
logger.error(f"Error loading tokenizer for model {name}. The model may not exist or is not accessible with the provided token. Error: {e}")
continue # Skip to the next model if the tokenizer can't be loaded
chktok = tokenizer.encode(chktxt)
chktok = tokenizer.encode(CHK_TXT)
chkhsh = sha256(str(chktok).encode()).hexdigest()
logger.info(f"model: {name}")
@ -192,7 +192,7 @@ src_func = f"""
# we will use this unique identifier to write a "tokenizer.ggml.pre" entry in the GGUF file which we can
# use in llama.cpp to implement the same pre-tokenizer
chktxt = {repr(chktxt)}
chktxt = {repr(CHK_TXT)}
chktok = tokenizer.encode(chktxt)
chkhsh = sha256(str(chktok).encode()).hexdigest()
@ -288,7 +288,7 @@ tests = [
"333333333",
"Cửa Việt", # llama-bpe fails on this
" discards",
chktxt,
CHK_TXT,
]
# write the tests to ./models/ggml-vocab-{name}.gguf.inp