mod gpt
This commit is contained in:
parent
0b9bb7a371
commit
2cdf954b50
2
gpt.py
2
gpt.py
|
|
@ -8,7 +8,7 @@ from datasets import Dataset
|
||||||
os.environ["TOKENIZERS_PARALLELISM"] = "false"
|
os.environ["TOKENIZERS_PARALLELISM"] = "false"
|
||||||
MODEL_NAME = "gpt2"
|
MODEL_NAME = "gpt2"
|
||||||
SPECIAL_TOKENS = ["[CITATION_START]", "[CITATION_END]"]
|
SPECIAL_TOKENS = ["[CITATION_START]", "[CITATION_END]"]
|
||||||
TEXT_FILE_PATH = "scieżka/do/pliku_z_kodeksem.txt" # Zmień na właściwą ścieżkę
|
TEXT_FILE_PATH = "./docs/kodekspracy.txt" # Zmień na właściwą ścieżkę
|
||||||
|
|
||||||
def prepare_dataset_from_file(file_path):
|
def prepare_dataset_from_file(file_path):
|
||||||
with open(file_path, 'r', encoding='utf-8') as f:
|
with open(file_path, 'r', encoding='utf-8') as f:
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue