transformers 4.41.0 breaks generate() for T5

[abdulfatir]

System Info

• transformers version: 4.41.0
• Platform: Linux-5.15.0-1033-aws-x86_64-with-glibc2.31
• Python version: 3.10.9
• Huggingface_hub version: 0.23.0
• Safetensors version: 0.4.3
• Accelerate version: 0.30.0
• Accelerate config: not found
• PyTorch version (GPU?): 2.3.0+cu121 (True)
• Tensorflow version (GPU?): not installed (NA)
• Flax version (CPU?/GPU?/TPU?): not installed (NA)
• Jax version: not installed
• JaxLib version: not installed
• Using GPU in script?: Yes
• Using distributed or parallel set-up in script?: No

Who can help?

@ArthurZucker and @younesbelkada

Information

• The official example scripts
• My own modified scripts

Tasks

• An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
• My own task or dataset (give details below)

Reproduction

The following code breaks in v4.41.0 (it works on earlier versions).

import torch
from transformers import GenerationConfig
from transformers import T5ForConditionalGeneration

model = T5ForConditionalGeneration.from_pretrained(
    "google/t5-efficient-tiny", device_map="cuda"
)
input_ids = torch.tensor([[4, 5, 6, 6, 7]], device="cuda")
model.generate(
    input_ids=input_ids,
    generation_config=GenerationConfig(do_sample=True),
)

Error:

ValueError: `decoder_start_token_id` or `bos_token_id` has to be defined for encoder-decoder generation.

Expected behavior

Expected generate to work like before without manually specifying decoder_start_token_id or bos_token_id in the GenerationConfig.

[younesbelkada]

Thanks @abdulfatir !
#30899 from @zucchini-nlp should fix the issue ! :)