SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Fix undeterministic order in modular dependencies (#39005)

Browse Source 
* sort correctly

* Update modeling_minimax.py

* Update modular_model_converter.py
This commit is contained in:
Cyril Vallez
2025-06-24 17:04:33 +02:00
committed by GitHub
parent bdf5fb70aa
commit e1e11b0299
14 changed files with 236 additions and 1600 deletions
Download Patch File Download Diff File Expand all files Collapse all files

97
examples/modular-transformers/modeling_new_task_model.py
View File

@@ -22,68 +22,48 @@ from .configuration_new_task_model import NewTaskModelConfig
@dataclass
class NewTaskModelModelOutputWithPast(BaseModelOutputWithPast):
"""
@auto_docstring(
custom_intro="""
Base class for NewTaskModel outputs, with hidden states and attentions.
"""
)
class NewTaskModelModelOutputWithPast(BaseModelOutputWithPast):
r"""
past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape
`(batch_size, num_heads, sequence_length, embed_size_per_head)`)
Args:
last_hidden_state (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
Sequence of hidden-states at the output of the last layer of the model.
past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape
`(batch_size, num_heads, sequence_length, embed_size_per_head)`)
Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see
`past_key_values` input) to speed up sequential decoding.
hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
image_hidden_states (`torch.FloatTensor`, *optional*):
A `torch.FloatTensor` of size `(batch_size, num_images, sequence_length, hidden_size)`.
image_hidden_states of the model produced by the vision encoder and after projecting the last hidden state.
Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see
`past_key_values` input) to speed up sequential decoding.
image_hidden_states (`torch.FloatTensor`, *optional*):
A `torch.FloatTensor` of size `(batch_size, num_images, sequence_length, hidden_size)`.
image_hidden_states of the model produced by the vision encoder and after projecting the last hidden state.
"""
image_hidden_states: Optional[torch.FloatTensor] = None
@dataclass
class NewTaskModelCausalLMOutputWithPast(ModelOutput):
"""
@auto_docstring(
custom_intro="""
Base class for NewTaskModel causal language model (or autoregressive) outputs.
"""
)
class NewTaskModelCausalLMOutputWithPast(ModelOutput):
r"""
loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
Language modeling loss (for next-token prediction).
logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.text_config.vocab_size)`):
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape
`(batch_size, num_heads, sequence_length, embed_size_per_head)`)
Args:
loss (`torch.FloatTensor` of shape `(1,)`, *optional*, returned when `labels` is provided):
Language modeling loss (for next-token prediction).
logits (`torch.FloatTensor` of shape `(batch_size, sequence_length, config.text_config.vocab_size)`):
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
past_key_values (`tuple(tuple(torch.FloatTensor))`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
Tuple of `tuple(torch.FloatTensor)` of length `config.n_layers`, with each tuple having 2 tensors of shape
`(batch_size, num_heads, sequence_length, embed_size_per_head)`)
Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see
`past_key_values` input) to speed up sequential decoding.
hidden_states (`tuple(torch.FloatTensor)`, *optional*, returned when `output_hidden_states=True` is passed or when `config.output_hidden_states=True`):
Tuple of `torch.FloatTensor` (one for the output of the embeddings, if the model has an embedding layer, +
one for the output of each layer) of shape `(batch_size, sequence_length, hidden_size)`.
Hidden-states of the model at the output of each layer plus the optional initial embedding outputs.
attentions (`tuple(torch.FloatTensor)`, *optional*, returned when `output_attentions=True` is passed or when `config.output_attentions=True`):
Tuple of `torch.FloatTensor` (one for each layer) of shape `(batch_size, num_heads, sequence_length,
sequence_length)`.
Attentions weights after the attention softmax, used to compute the weighted average in the self-attention
heads.
image_hidden_states (`torch.FloatTensor`, *optional*):
A `torch.FloatTensor` of size `(batch_size, num_images, sequence_length, hidden_size)`.
image_hidden_states of the model produced by the vision encoder after projecting last hidden state.
Contains pre-computed hidden-states (key and values in the self-attention blocks) that can be used (see
`past_key_values` input) to speed up sequential decoding.
image_hidden_states (`torch.FloatTensor`, *optional*):
A `torch.FloatTensor` of size `(batch_size, num_images, sequence_length, hidden_size)`.
image_hidden_states of the model produced by the vision encoder after projecting last hidden state.
"""
loss: Optional[torch.FloatTensor] = None
@@ -157,6 +137,12 @@ class NewTaskModelModel(NewTaskModelPreTrainedModel):
def set_input_embeddings(self, value):
self.language_model.set_input_embeddings(value)
def set_decoder(self, decoder):
self.language_model = decoder
def get_decoder(self):
return self.language_model
def _update_causal_mask(
self,
attention_mask,
@@ -406,10 +392,13 @@ class NewTaskModelForNewTask(NewTaskModelPreTrainedModel, GenerationMixin):
self.lm_head = new_embeddings
def set_decoder(self, decoder):
self.model = decoder
self.model.set_decoder(decoder)
def get_decoder(self):
return self.model
return self.model.get_decoder()
def get_image_features(self, pixel_values):
return self.model.get_image_features(pixel_values)
# Make modules available throught conditional class for BC
@property