doc-to-lora/tmp/test_detokenize.py
2025-09-28 15:46:47 +00:00

35 lines
1.4 KiB
Python

from ctx_to_lora.model_loading import get_tokenizer
model_name_or_path = "google/gemma-2-2b-it"
tokenizer = get_tokenizer(model_name_or_path, train=True)
qa = (
"Architecturally, the school has a Catholic character. "
"Atop the Main Building's gold dome is a golden statue of the Virgin Mary. "
"Immediately in front of the Main Building and facing it, "
'is a copper statue of Christ with arms upraised with the legend "Venite Ad Me Omnes". '
"Next to the Main Building is the Basilica of the Sacred Heart. "
"Immediately behind the basilica is the Grotto, a Marian place of prayer and reflection. "
"It is a replica of the grotto at Lourdes, "
"France where the Virgin Mary reputedly appeared to Saint Bernadette Soubirous "
"in 1858. At the end of the main drive (and in a direct line that connects through 3 "
"statues and the Gold Dome), is a simple, modern stone statue of Mary."
"\n\nAnswer the following question. "
"Output only the answer and do not output any other words."
"\n\nQuestion: To whom did the Virgin Mary allegedly appear in 1858 in Lourdes France?"
)
messages = [{"role": "system", "content": ""}, {"role": "user", "content": qa}]
chat_ids = tokenizer.apply_chat_template(
messages,
tokenize=True,
add_special_token=False,
add_generation_prompt=True,
return_tensors="pt",
return_dict=True,
)
print(chat_ids)
print(tokenizer.batch_decode(chat_ids["input_ids"]))
breakpoint()