Skip to content

fix code for transformers>=4.50.0,<5.0.0 #47

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Lee-xeo wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix code for transformers>=4.50.0,<5.0.0 #47

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
accelerate>=1.9.0
torch==2.6.0
torchaudio==2.6.0
transformers==4.49.0
transformers>=4.50.0,<5.0.0
fastapi>=0.116.1
librosa>=0.11.0
pydantic>=2.11.7
Expand Down
13 changes: 10 additions & 3 deletions src/mimo_audio/modeling_mimo_audio.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@
from transformers.generation.utils import (
GenerateOutput,
GenerationConfig,
GenerationMixin,
StoppingCriteriaList,
is_deepspeed_zero3_enabled,
)
Expand Down Expand Up @@ -221,7 +222,12 @@ def to_dict(self):
}


class MiMoAudioForCausalLM(Qwen2PreTrainedModel):
class MiMoAudioForCausalLM(Qwen2PreTrainedModel, GenerationMixin):
# transformers>=4.50 移除了 PreTrainedModel._supports_cache_class，
# 但 prepare_inputs_for_generation 中仍引用它来决定是否传递 cache_position。
# MiMo 使用 DynamicCache，显式声明为 True。
_supports_cache_class = True

def __init__(
self,
config: MiMoAudioConfig | Qwen2Config,
Expand Down Expand Up @@ -746,9 +752,10 @@ def slm_sample(
this_peer_finished,
synced_gpus,
device=input_ids.device,
cur_len=cur_len,
max_length=max_length,
):
# 长度检查（transformers>=4.50 不再由 _has_unfinished_sequences 负责）
if cur_len >= max_length:
break
# prepare model inputs
model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)

Expand Down