File size: 15,674 Bytes
3567964
 
 
 
 
 
 
 
 
9082859
3567964
 
 
 
 
 
 
 
 
 
357996b
3567964
 
 
 
 
9082859
 
 
 
 
 
 
 
3567964
 
 
8f6bbf9
705d04a
3567964
 
900d017
3567964
 
9082859
3567964
 
 
 
 
 
 
 
357996b
900d017
 
3567964
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0e6d592
 
3567964
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8f6bbf9
3567964
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9082859
 
 
3567964
 
 
9082859
 
 
 
 
3567964
 
 
9082859
 
 
3567964
 
 
9082859
 
 
3567964
7c84c28
3567964
 
 
9082859
 
 
3567964
9082859
3567964
 
8f6bbf9
 
3567964
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0e6d592
3567964
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8f6bbf9
 
3567964
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
# --------------------------------------------------------
# InternVL
# Copyright (c) 2024 OpenGVLab
# Licensed under The MIT License [see LICENSE for details]
# --------------------------------------------------------
import warnings
from typing import Any, List, Optional, Tuple, Union

import torch.utils.checkpoint
import transformers
from torch import nn
from torch.nn import CrossEntropyLoss
from transformers import (AutoModel, GenerationConfig, LlamaForCausalLM,
                          LlamaTokenizer)
from transformers.modeling_outputs import CausalLMOutputWithPast
from transformers.modeling_utils import PreTrainedModel
from transformers.utils import ModelOutput, logging

from .configuration_internvl_chat import InternVLChatConfig
from .conversation import get_conv_template
from .modeling_intern_vit import InternVisionModel, has_flash_attn
from .modeling_internlm2 import InternLM2ForCausalLM

logger = logging.get_logger(__name__)


def version_cmp(v1, v2, op='eq'):
    import operator

    from packaging import version
    op_func = getattr(operator, op)
    return op_func(version.parse(v1), version.parse(v2))


class InternVLChatModel(PreTrainedModel):
    config_class = InternVLChatConfig
    main_input_name = 'pixel_values'
    base_model_prefix = 'language_model'
    _supports_flash_attn_2 = True
    _no_split_modules = ['InternVisionModel', 'LlamaDecoderLayer', 'InternLM2DecoderLayer']

    def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None, use_flash_attn=True):
        super().__init__(config)

        assert version_cmp(transformers.__version__, '4.36.2', 'ge')
        image_size = config.force_image_size or config.vision_config.image_size
        patch_size = config.vision_config.patch_size
        self.patch_size = patch_size
        self.select_layer = config.select_layer
        self.template = config.template
        self.num_image_token = int((image_size // patch_size) ** 2 * (config.downsample_ratio ** 2))
        self.downsample_ratio = config.downsample_ratio
        self.ps_version = config.ps_version
        use_flash_attn = use_flash_attn if has_flash_attn else False
        config.vision_config.use_flash_attn = True if use_flash_attn else False
        config.llm_config.attn_implementation = 'flash_attention_2' if use_flash_attn else 'eager'

        logger.info(f'num_image_token: {self.num_image_token}')
        logger.info(f'ps_version: {self.ps_version}')
        if vision_model is not None:
            self.vision_model = vision_model
        else:
            self.vision_model = InternVisionModel(config.vision_config)
        if language_model is not None:
            self.language_model = language_model
        else:
            if config.llm_config.architectures[0] == 'LlamaForCausalLM':
                self.language_model = LlamaForCausalLM(config.llm_config)
            elif config.llm_config.architectures[0] == 'InternLM2ForCausalLM':
                self.language_model = InternLM2ForCausalLM(config.llm_config)
            else:
                raise NotImplementedError(f'{config.llm_config.architectures[0]} is not implemented.')

        vit_hidden_size = config.vision_config.hidden_size
        llm_hidden_size = config.llm_config.hidden_size

        self.mlp1 = nn.Sequential(
            nn.LayerNorm(vit_hidden_size * int(1 / self.downsample_ratio) ** 2),
            nn.Linear(vit_hidden_size * int(1 / self.downsample_ratio) ** 2, llm_hidden_size),
            nn.GELU(),
            nn.Linear(llm_hidden_size, llm_hidden_size)
        )

        self.img_context_token_id = None
        self.conv_template = get_conv_template(self.template)
        self.system_message = self.conv_template.system_message

    def forward(
            self,
            pixel_values: torch.FloatTensor,
            input_ids: torch.LongTensor = None,
            attention_mask: Optional[torch.Tensor] = None,
            position_ids: Optional[torch.LongTensor] = None,
            image_flags: Optional[torch.LongTensor] = None,
            past_key_values: Optional[List[torch.FloatTensor]] = None,
            labels: Optional[torch.LongTensor] = None,
            use_cache: Optional[bool] = None,
            output_attentions: Optional[bool] = None,
            output_hidden_states: Optional[bool] = None,
            return_dict: Optional[bool] = None,
    ) -> Union[Tuple, CausalLMOutputWithPast]:
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        image_flags = image_flags.squeeze(-1)
        input_embeds = self.language_model.get_input_embeddings()(input_ids).clone()

        vit_embeds = self.extract_feature(pixel_values)
        vit_embeds = vit_embeds[image_flags == 1]
        vit_batch_size = pixel_values.shape[0]

        B, N, C = input_embeds.shape
        input_embeds = input_embeds.reshape(B * N, C)

        if torch.distributed.get_rank() == 0:
            print(f'dynamic ViT batch size: {vit_batch_size}, images per sample: {vit_batch_size / B}, dynamic token length: {N}')

        input_ids = input_ids.reshape(B * N)
        selected = (input_ids == self.img_context_token_id)
        try:
            input_embeds[selected] = input_embeds[selected] * 0.0 + vit_embeds.reshape(-1, C)
        except Exception as e:
            vit_embeds = vit_embeds.reshape(-1, C)
            print(f'warning: {e}, input_embeds[selected].shape={input_embeds[selected].shape}, '
                  f'vit_embeds.shape={vit_embeds.shape}')
            n_token = selected.sum()
            input_embeds[selected] = input_embeds[selected] * 0.0 + vit_embeds[:n_token]

        input_embeds = input_embeds.reshape(B, N, C)

        outputs = self.language_model(
            inputs_embeds=input_embeds,
            attention_mask=attention_mask,
            position_ids=position_ids,
            past_key_values=past_key_values,
            use_cache=use_cache,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )
        logits = outputs.logits

        loss = None
        if labels is not None:
            # Shift so that tokens < n predict n
            shift_logits = logits[..., :-1, :].contiguous()
            shift_labels = labels[..., 1:].contiguous()
            # Flatten the tokens
            loss_fct = CrossEntropyLoss()
            shift_logits = shift_logits.view(-1, self.language_model.config.vocab_size)
            shift_labels = shift_labels.view(-1)
            # Enable model parallelism
            shift_labels = shift_labels.to(shift_logits.device)
            loss = loss_fct(shift_logits, shift_labels)

        if not return_dict:
            output = (logits,) + outputs[1:]
            return (loss,) + output if loss is not None else output

        return CausalLMOutputWithPast(
            loss=loss,
            logits=logits,
            past_key_values=outputs.past_key_values,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

    def pixel_shuffle(self, x, scale_factor=0.5):
        n, w, h, c = x.size()
        # N, W, H, C --> N, W, H * scale, C // scale
        x = x.view(n, w, int(h * scale_factor), int(c / scale_factor))
        # N, W, H * scale, C // scale --> N, H * scale, W, C // scale
        x = x.permute(0, 2, 1, 3).contiguous()
        # N, H * scale, W, C // scale --> N, H * scale, W * scale, C // (scale ** 2)
        x = x.view(n, int(h * scale_factor), int(w * scale_factor),
                   int(c / (scale_factor * scale_factor)))
        if self.ps_version == 'v1':
            warnings.warn("In ps_version 'v1', the height and width have not been swapped back, "
                          'which results in a transposed image.')
        else:
            x = x.permute(0, 2, 1, 3).contiguous()
        return x

    def extract_feature(self, pixel_values):
        if self.select_layer == -1:
            vit_embeds = self.vision_model(
                pixel_values=pixel_values,
                output_hidden_states=False,
                return_dict=True).last_hidden_state
        else:
            vit_embeds = self.vision_model(
                pixel_values=pixel_values,
                output_hidden_states=True,
                return_dict=True).hidden_states[self.select_layer]
        vit_embeds = vit_embeds[:, 1:, :]

        h = w = int(vit_embeds.shape[1] ** 0.5)
        vit_embeds = vit_embeds.reshape(vit_embeds.shape[0], h, w, -1)
        vit_embeds = self.pixel_shuffle(vit_embeds, scale_factor=self.downsample_ratio)
        vit_embeds = vit_embeds.reshape(vit_embeds.shape[0], -1, vit_embeds.shape[-1])
        vit_embeds = self.mlp1(vit_embeds)
        return vit_embeds

    def batch_chat(self, tokenizer, pixel_values, questions, generation_config, num_patches_list=None,
                   history=None, return_history=False, IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>',
                   IMG_CONTEXT_TOKEN='<IMG_CONTEXT>', verbose=False, image_counts=None):
        if history is not None or return_history:
            print('Now multi-turn chat is not supported in batch_chat.')
            raise NotImplementedError

        if image_counts is not None:
            num_patches_list = image_counts
            print('Warning: `image_counts` is deprecated. Please use `num_patches_list` instead.')

        img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
        self.img_context_token_id = img_context_token_id

        if verbose and pixel_values is not None:
            image_bs = pixel_values.shape[0]
            print(f'dynamic ViT batch size: {image_bs}')

        queries = []
        for idx, num_patches in enumerate(num_patches_list):
            question = questions[idx]
            if pixel_values is not None and '<image>' not in question:
                question = '<image>\n' + question
            template = get_conv_template(self.template)
            template.system_message = self.system_message
            template.append_message(template.roles[0], question)
            template.append_message(template.roles[1], None)
            query = template.get_prompt()

            image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token * num_patches + IMG_END_TOKEN
            query = query.replace('<image>', image_tokens, 1)
            queries.append(query)

        tokenizer.padding_side = 'left'
        model_inputs = tokenizer(queries, return_tensors='pt', padding=True)
        input_ids = model_inputs['input_ids'].to(self.device)
        attention_mask = model_inputs['attention_mask'].to(self.device)
        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)
        generation_config['eos_token_id'] = eos_token_id
        generation_output = self.generate(
            pixel_values=pixel_values,
            input_ids=input_ids,
            attention_mask=attention_mask,
            **generation_config
        )
        responses = tokenizer.batch_decode(generation_output, skip_special_tokens=True)
        responses = [response.split(template.sep)[0].strip() for response in responses]
        return responses

    def chat(self, tokenizer, pixel_values, question, generation_config, history=None, return_history=False,
             num_patches_list=None, IMG_START_TOKEN='<img>', IMG_END_TOKEN='</img>', IMG_CONTEXT_TOKEN='<IMG_CONTEXT>',
             verbose=False):

        if history is None and pixel_values is not None and '<image>' not in question:
            question = '<image>\n' + question

        if num_patches_list is None:
            num_patches_list = [pixel_values.shape[0]] if pixel_values is not None else []
        assert pixel_values is None or len(pixel_values) == sum(num_patches_list)

        img_context_token_id = tokenizer.convert_tokens_to_ids(IMG_CONTEXT_TOKEN)
        self.img_context_token_id = img_context_token_id

        template = get_conv_template(self.template)
        template.system_message = self.system_message
        eos_token_id = tokenizer.convert_tokens_to_ids(template.sep)

        history = [] if history is None else history
        for (old_question, old_answer) in history:
            template.append_message(template.roles[0], old_question)
            template.append_message(template.roles[1], old_answer)
        template.append_message(template.roles[0], question)
        template.append_message(template.roles[1], None)
        query = template.get_prompt()

        if verbose and pixel_values is not None:
            image_bs = pixel_values.shape[0]
            print(f'dynamic ViT batch size: {image_bs}')

        for num_patches in num_patches_list:
            image_tokens = IMG_START_TOKEN + IMG_CONTEXT_TOKEN * self.num_image_token * num_patches + IMG_END_TOKEN
            query = query.replace('<image>', image_tokens, 1)

        model_inputs = tokenizer(query, return_tensors='pt')
        input_ids = model_inputs['input_ids'].to(self.device)
        attention_mask = model_inputs['attention_mask'].to(self.device)
        generation_config['eos_token_id'] = eos_token_id
        generation_output = self.generate(
            pixel_values=pixel_values,
            input_ids=input_ids,
            attention_mask=attention_mask,
            **generation_config
        )
        response = tokenizer.batch_decode(generation_output, skip_special_tokens=True)[0]
        response = response.split(template.sep)[0].strip()
        history.append((question, response))
        if return_history:
            return response, history
        else:
            query_to_print = query.replace(IMG_CONTEXT_TOKEN, '')
            query_to_print = query_to_print.replace(f'{IMG_START_TOKEN}{IMG_END_TOKEN}', '<image>')
            if verbose:
                print(query_to_print, response)
            return response

    @torch.no_grad()
    def generate(
            self,
            pixel_values: Optional[torch.FloatTensor] = None,
            input_ids: Optional[torch.FloatTensor] = None,
            attention_mask: Optional[torch.LongTensor] = None,
            visual_features: Optional[torch.FloatTensor] = None,
            generation_config: Optional[GenerationConfig] = None,
            output_hidden_states: Optional[bool] = None,
            return_dict: Optional[bool] = None,
            **generate_kwargs,
    ) -> torch.LongTensor:

        assert self.img_context_token_id is not None
        if pixel_values is not None:
            if visual_features is not None:
                vit_embeds = visual_features
            else:
                vit_embeds = self.extract_feature(pixel_values)
            input_embeds = self.language_model.get_input_embeddings()(input_ids)
            B, N, C = input_embeds.shape
            input_embeds = input_embeds.reshape(B * N, C)

            input_ids = input_ids.reshape(B * N)
            selected = (input_ids == self.img_context_token_id)
            assert selected.sum() != 0
            input_embeds[selected] = vit_embeds.reshape(-1, C).to(input_embeds.device)

            input_embeds = input_embeds.reshape(B, N, C)
        else:
            input_embeds = self.language_model.get_input_embeddings()(input_ids)

        outputs = self.language_model.generate(
            inputs_embeds=input_embeds,
            attention_mask=attention_mask,
            generation_config=generation_config,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
            use_cache=True,
            **generate_kwargs,
        )

        return outputs