from dataclasses import dataclass
from typing import Optional
import torch
from transformers.modeling_outputs import ModelOutput
from transformers.utils import auto_docstring
from transformers.cache_utils import Cache
@dataclass
@auto_docstring(
custom_intro="""
Base class for Qwen3VL causal language model (or autoregressive) outputs.
"""
)
class Qwen3VLCausalLMOutputWithPast(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.vocab_size)`):
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
It is a [`~cache_utils.Cache`] instance. For more details, see our [kv cache guide](https://huggingface.co/docs/transformers/en/kv_cache).
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.
rope_deltas (`torch.LongTensor` of shape `(batch_size, )`, *optional*):
The rope index difference between sequence length and multimodal rope.
"""
loss: Optional[torch.FloatTensor] = None
logits: Optional[torch.FloatTensor] = None
past_key_values: Optional[Cache] = None
hidden_states: Optional[tuple[torch.FloatTensor]] = None
attentions: Optional[tuple[torch.FloatTensor]] = None
rope_deltas: Optional[torch.LongTensor] = None
@dataclass
@auto_docstring(
custom_intro="""
Base class for Llava outputs, with hidden states and attentions.
"""
)
class Qwen3VLModelOutputWithPast(ModelOutput):
r"""
past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
It is a [`~cache_utils.Cache`] instance.
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.
rope_deltas (`torch.LongTensor` of shape `(batch_size, )`, *optional*):
The rope index difference between sequence length and multimodal rope.
"""
last_hidden_state: Optional[torch.FloatTensor] = None
past_key_values: Optional[Cache] = None
hidden_states: Optional[tuple[torch.FloatTensor]] = None
attentions: Optional[tuple[torch.FloatTensor]] = None
rope_deltas: Optional[torch.LongTensor] = None
@dataclass
@auto_docstring(
custom_intro="""
Base class for Qwen3VLMoe causal language model (or autoregressive) outputs.
"""
)
class Qwen3VLMoeCausalLMOutputWithPast(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.vocab_size)`):
Prediction scores of the language modeling head (scores for each vocabulary token before SoftMax).
past_key_values (`Cache`, *optional*, returned when `use_cache=True` is passed or when `config.use_cache=True`):
It is a [`~cache_utils.Cache`] instance.
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.
rope_deltas (`torch.LongTensor` of shape `(batch_size, )`, *optional*):
The rope index difference between sequence length and multimodal rope.
"""
loss: Optional[torch.FloatTensor] = None
logits: Optional[torch.FloatTensor] = None
past_key_values: Optional[Cache] = None
hidden_states: Optional[tuple[torch.FloatTensor]] = None
attentions: Optional[tuple[torch.FloatTensor]] = None
rope_deltas: Optional[torch.LongTensor] = None
aux_loss: Optional[torch.FloatTensor] = None
