wassname/Open-Assistant
1
0
Fork 0
mirror of https://github.com/wassname/Open-Assistant.git synced 2026-09-09 11:15:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

add docstring info about tokenizer matching

Browse Source
This commit is contained in:
jack.butler
2023-02-10 09:46:58 +00:00
parent 090c5cbcc2
commit 2fbf2fa457
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
model/supervised_finetuning/utils.py
+5 -2
View File
@@ -36,8 +36,11 @@ TOKENIZER_CONFIGS = {
def match_tokenizer_name(model_name: str) -> TokenizerConfig: def match_tokenizer_name(model_name: str) -> TokenizerConfig:
"""Match a partial model name to a tokenizer configuration""" """
tokenizer_config_matches = [config for name, config in TOKENIZER_CONFIGS.items() if model_name in name] Match a partial model name to a tokenizer configuration
i.e. model_name `Salesforce/codegen-2B-multi` has config name `codegen`
"""
tokenizer_config_matches = [config for name, config in TOKENIZER_CONFIGS.items() if name in model_name]
if not tokenizer_config_matches: if not tokenizer_config_matches:
raise ValueError(f"Cannot find any tokeniser configuration to match {model_name=}") raise ValueError(f"Cannot find any tokeniser configuration to match {model_name=}")
elif 1 < len(tokenizer_config_matches): elif 1 < len(tokenizer_config_matches):