2024-12-29 14:07:19.289094: I tensorflow/core/util/port.
cc:153] oneDNN custom
operations are on. You may see slightly different numerical results due to
floating-point round-off errors from different computation orders. To turn them
off,
set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2024-12-29 14:07:22.929358: I tensorflow/core/util/[Link]] oneDNN custom
operations are on. You may see slightly different numerical results due to
floating-point round-off errors from different computation orders. To turn them
off,
set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
Setting `pad_token_id` to `eos_token_id`:50256 for open-end generation.
Traceback (most recent call last):
File "E:\VS_Code\[Link]", line 39, in <module>
response = generate_response(prompt) # Генерируем ответ
^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\VS_Code\[Link]", line 30, in generate_response
output = [Link](input_ids, attention_mask=attention_mask,
max_length=max_length, num_return_sequences=1, no_repeat_ngram_size=2)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\user\AppData\Local\Programs\Python\Python311\Lib\site-packages\
torch\utils\_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\user\AppData\Local\Programs\Python\Python311\Lib\site-packages\
transformers\generation\[Link]", line 2105, in generate
self._validate_generated_length(generation_config, input_ids_length,
has_default_max_length)
File "C:\Users\user\AppData\Local\Programs\Python\Python311\Lib\site-packages\
transformers\generation\[Link]", line 1411, in _validate_generated_length
raise ValueError(
ValueError: Input length of input_ids is 1683, but `max_length` is set to 1500.
This can lead to unexpected behavior. You should consider increasing `max_length`
or, better yet, setting `max_new_tokens`.