File size: 5,237 Bytes
a65550c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
#    Copyright 2024 Hao Zhang
#
#    Licensed under the Apache License, Version 2.0 (the "License");
#    you may not use this file except in compliance with the License.
#    You may obtain a copy of the License at
#
#        http://www.apache.org/licenses/LICENSE-2.0
#
#    Unless required by applicable law or agreed to in writing, software
#    distributed under the License is distributed on an "AS IS" BASIS,
#    WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
#    See the License for the specific language governing permissions and
#    limitations under the License.


from typing import List, Optional, Tuple, Union, Dict
import torch
import torch.nn as nn
from torch.nn import CrossEntropyLoss

import transformers
from transformers import AutoConfig, AutoModelForCausalLM

from transformers.modeling_outputs import CausalLMOutputWithPast
from transformers.generation.utils import GenerateOutput

# from ...constants import IGNORE_INDEX, IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN
from llava.model.llava_arch import LlavaMetaModel, LlavaMetaForCausalLM
from transformers import Qwen2MoeConfig, Qwen2MoeModel, Qwen2MoeForCausalLM

# from .qwen.modeling_qwen import QWenLMHeadModel, QWenModel
# from .qwen.configuration_qwen import QWenConfig


class LlavaQwenMoeConfig(Qwen2MoeConfig):
    model_type = "llava_qwen_moe"


class LlavaQwenMoeModel(LlavaMetaModel, Qwen2MoeModel):
    config_class = LlavaQwenMoeConfig

    def __init__(self, config: Qwen2MoeConfig):
        super(LlavaQwenMoeModel, self).__init__(config)


class LlavaQwenMoeForCausalLM(Qwen2MoeForCausalLM, LlavaMetaForCausalLM):
    config_class = LlavaQwenMoeConfig

    def __init__(self, config):
        # super(Qwen2MoeForCausalLM, self).__init__(config)
        Qwen2MoeForCausalLM.__init__(self, config)
        config.model_type = "llava_qwen_moe"
        config.rope_scaling = None

        self.model = LlavaQwenMoeModel(config)
        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
        # Initialize weights and apply final processing
        self.post_init()

    def get_model(self):
        return self.model

    def forward(
        self,
        input_ids: torch.LongTensor = None,
        attention_mask: Optional[torch.Tensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        past_key_values: Optional[List[torch.FloatTensor]] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
        labels: Optional[torch.LongTensor] = None,
        use_cache: Optional[bool] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        images: Optional[torch.FloatTensor] = None,
        image_sizes: Optional[List[List[int]]] = None,
        return_dict: Optional[bool] = None,
        cache_position=None,
    ) -> Union[Tuple, CausalLMOutputWithPast]:

        if inputs_embeds is None:
            (input_ids, position_ids, attention_mask, past_key_values, inputs_embeds, labels) = self.prepare_inputs_labels_for_multimodal(input_ids, position_ids, attention_mask, past_key_values, labels, images, image_sizes)

        return super().forward(
            input_ids=input_ids,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_values=past_key_values,
            inputs_embeds=inputs_embeds,
            labels=labels,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

    @torch.no_grad()
    def generate(
        self,
        inputs: Optional[torch.Tensor] = None,
        images: Optional[torch.Tensor] = None,
        image_sizes: Optional[torch.Tensor] = None,
        **kwargs,
    ) -> Union[GenerateOutput, torch.LongTensor]:
        position_ids = kwargs.pop("position_ids", None)
        attention_mask = kwargs.pop("attention_mask", None)
        if "inputs_embeds" in kwargs:
            raise NotImplementedError("`inputs_embeds` is not supported")

        if images is not None:
            (inputs, position_ids, attention_mask, _, inputs_embeds, _) = self.prepare_inputs_labels_for_multimodal(inputs, position_ids, attention_mask, None, None, images, image_sizes=image_sizes)
        else:
            inputs_embeds = self.get_model().embed_tokens(inputs)

        return super().generate(position_ids=position_ids, attention_mask=attention_mask, inputs_embeds=inputs_embeds, **kwargs)

    def prepare_inputs_for_generation(self, input_ids, past_key_values=None, inputs_embeds=None, **kwargs):
        images = kwargs.pop("images", None)
        image_sizes = kwargs.pop("image_sizes", None)
        inputs = super().prepare_inputs_for_generation(input_ids, past_key_values=past_key_values, inputs_embeds=inputs_embeds, **kwargs)
        if images is not None:
            inputs["images"] = images
        if image_sizes is not None:
            inputs["image_sizes"] = image_sizes
        return inputs


AutoConfig.register("llava_qwen_moe", LlavaQwenMoeConfig)
AutoModelForCausalLM.register(LlavaQwenMoeConfig, LlavaQwenMoeForCausalLM)