sealofyou/InternVVL3_5-Lora-SFT-3750-steps-baseline
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: sealofyou/InternVVL3_5-Lora-SFT-3750-steps-baseline
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-01 15:44:15 +08:00
commit 8b9d8b9be6
20 changed files with 911357 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
.gitattributes vendored Normal file
View File

@@ -0,0 +1,47 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bin.* filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zstandard filter=lfs diff=lfs merge=lfs -text
*.tfevents* filter=lfs diff=lfs merge=lfs -text
*.db* filter=lfs diff=lfs merge=lfs -text
*.ark* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.gguf* filter=lfs diff=lfs merge=lfs -text
*.ggml filter=lfs diff=lfs merge=lfs -text
*.llamafile* filter=lfs diff=lfs merge=lfs -text
*.pt2 filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

2
.gitignore vendored Normal file
View File

@@ -0,0 +1,2 @@
runs/
images/

37
added_tokens.json Normal file
View File

@@ -0,0 +1,37 @@
{
"</box>": 151677,
"</img>": 151670,
"</quad>": 151673,
"</ref>": 151675,
"</think>": 151668,
"</tool_call>": 151658,
"</tool_response>": 151666,
"<IMG_CONTEXT>": 151671,
"<box>": 151676,
"<img>": 151669,
"<quad>": 151672,
"<ref>": 151674,
"<think>": 151667,
"<tool_call>": 151657,
"<tool_response>": 151665,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

345
args.json Normal file
View File

File diff suppressed because one or more lines are too long

6
chat_template.jinja Normal file
View File

@@ -0,0 +1,6 @@
{% for message in messages %}{{'<|im_start|>' + message['role'] + '
'}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<image>
' }}{% elif content['type'] == 'video' %}{{ '<video>
' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
' }}{% endif %}

129
config.json Normal file
View File

@@ -0,0 +1,129 @@
{
"architectures": [
"InternVLChatModel"
],
"auto_map": {
"AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
"AutoModel": "modeling_internvl_chat.InternVLChatModel",
"AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
},
"downsample_ratio": 0.5,
"dtype": "bfloat16",
"dynamic_image_size": true,
"eos_token_id": 151645,
"force_image_size": 448,
"hidden_size": 1024,
"keys_to_ignore_at_inference": [
"past_key_values"
],
"llm_config": {
"_name_or_path": "/root/codespace/checkpoints/Qwen3-0.6B",
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"debug": false,
"dtype": "bfloat16",
"eos_token_id": 151645,
"ep_size": 1,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"micro_forward": false,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"skip_checkpoint": false,
"sliding_window": null,
"use_cache": false,
"use_deepep": false,
"use_sliding_window": false,
"vocab_size": 151936
},
"max_dynamic_patch": 12,
"min_dynamic_patch": 1,
"model_type": "internvl_chat",
"output_attentions": false,
"pad2square": false,
"pad_token_id": 151643,
"ps_version": "v2",
"select_layer": -1,
"template": "internvl2_5",
"tie_word_embeddings": false,
"transformers_version": null,
"use_backbone_lora": 0,
"use_llm_lora": 0,
"use_thumbnail": true,
"vision_config": {
"architectures": [
"InternVisionModel"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_intern_vit.InternVisionConfig",
"AutoModel": "modeling_intern_vit.InternVisionModel"
},
"drop_path_rate": 0.1,
"dropout": 0.0,
"dtype": "bfloat16",
"hidden_act": "gelu",
"hidden_size": 1024,
"image_size": 448,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 4096,
"layer_norm_eps": 1e-06,
"model_type": "intern_vit_6b",
"norm_type": "layer_norm",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 24,
"pad_token_id": 151643,
"patch_size": 14,
"qk_normalization": false,
"qkv_bias": true,
"use_fa3": false,
"use_flash_attn": false
}
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

119
configuration_intern_vit.py Normal file
View File

@@ -0,0 +1,119 @@
# --------------------------------------------------------
# InternVL
# Copyright (c) 2024 OpenGVLab
# Licensed under The MIT License [see LICENSE for details]
# --------------------------------------------------------
import os
from typing import Union
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
logger = logging.get_logger(__name__)
class InternVisionConfig(PretrainedConfig):
r"""
This is the configuration class to store the configuration of a [`InternVisionModel`]. It is used to
instantiate a vision encoder according to the specified arguments, defining the model architecture.
Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
documentation from [`PretrainedConfig`] for more information.
Args:
num_channels (`int`, *optional*, defaults to 3):
Number of color channels in the input images (e.g., 3 for RGB).
patch_size (`int`, *optional*, defaults to 14):
The size (resolution) of each patch.
image_size (`int`, *optional*, defaults to 224):
The size (resolution) of each image.
qkv_bias (`bool`, *optional*, defaults to `False`):
Whether to add a bias to the queries and values in the self-attention layers.
hidden_size (`int`, *optional*, defaults to 3200):
Dimensionality of the encoder layers and the pooler layer.
num_attention_heads (`int`, *optional*, defaults to 25):
Number of attention heads for each attention layer in the Transformer encoder.
intermediate_size (`int`, *optional*, defaults to 12800):
Dimensionality of the "intermediate" (i.e., feed-forward) layer in the Transformer encoder.
qk_normalization (`bool`, *optional*, defaults to `True`):
Whether to normalize the queries and keys in the self-attention layers.
num_hidden_layers (`int`, *optional*, defaults to 48):
Number of hidden layers in the Transformer encoder.
use_flash_attn (`bool`, *optional*, defaults to `True`):
Whether to use flash attention mechanism.
hidden_act (`str` or `function`, *optional*, defaults to `"gelu"`):
The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
`"relu"`, `"selu"` and `"gelu_new"` ``"gelu"` are supported.
layer_norm_eps (`float`, *optional*, defaults to 1e-6):
The epsilon used by the layer normalization layers.
dropout (`float`, *optional*, defaults to 0.0):
The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
drop_path_rate (`float`, *optional*, defaults to 0.0):
Dropout rate for stochastic depth.
attention_dropout (`float`, *optional*, defaults to 0.0):
The dropout ratio for the attention probabilities.
initializer_range (`float`, *optional*, defaults to 0.02):
The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
initializer_factor (`float`, *optional*, defaults to 0.1):
A factor for layer scale.
"""
model_type = 'intern_vit_6b'
def __init__(
self,
num_channels=3,
patch_size=14,
image_size=224,
qkv_bias=False,
hidden_size=3200,
num_attention_heads=25,
intermediate_size=12800,
qk_normalization=True,
num_hidden_layers=48,
use_flash_attn=True,
hidden_act='gelu',
norm_type='rms_norm',
layer_norm_eps=1e-6,
dropout=0.0,
drop_path_rate=0.0,
attention_dropout=0.0,
initializer_range=0.02,
initializer_factor=0.1,
**kwargs,
):
super().__init__(**kwargs)
self.hidden_size = hidden_size
self.intermediate_size = intermediate_size
self.dropout = dropout
self.drop_path_rate = drop_path_rate
self.num_hidden_layers = num_hidden_layers
self.num_attention_heads = num_attention_heads
self.num_channels = num_channels
self.patch_size = patch_size
self.image_size = image_size
self.initializer_range = initializer_range
self.initializer_factor = initializer_factor
self.attention_dropout = attention_dropout
self.layer_norm_eps = layer_norm_eps
self.hidden_act = hidden_act
self.norm_type = norm_type
self.qkv_bias = qkv_bias
self.qk_normalization = qk_normalization
self.use_flash_attn = use_flash_attn
@classmethod
def from_pretrained(cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs) -> 'PretrainedConfig':
config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
if 'vision_config' in config_dict:
config_dict = config_dict['vision_config']
if 'model_type' in config_dict and hasattr(cls, 'model_type') and config_dict['model_type'] != cls.model_type:
logger.warning(
f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
f'{cls.model_type}. This is not supported for all configurations of models and can yield errors.'
)
return cls.from_dict(config_dict, **kwargs)

115
configuration_internvl_chat.py Normal file
View File

@@ -0,0 +1,115 @@
# --------------------------------------------------------
# InternVL
# Copyright (c) 2024 OpenGVLab
# Licensed under The MIT License [see LICENSE for details]
# --------------------------------------------------------
import copy
from typing import Dict, Any, Optional
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
from .configuration_intern_vit import InternVisionConfig
logger = logging.get_logger(__name__)
class InternVLChatConfig(PretrainedConfig):
model_type = 'internvl_chat'
is_composition = True
def __init__(
self,
vision_config: Optional[Dict[str, Any]] = None,
llm_config: Optional[Dict[str, Any]] = None,
use_backbone_lora=0,
use_llm_lora=0,
select_layer=-1,
force_image_size=None,
downsample_ratio=0.5,
template=None,
dynamic_image_size=False,
use_thumbnail=False,
ps_version="v1",
min_dynamic_patch=1,
max_dynamic_patch=6,
**kwargs,
):
super().__init__(**kwargs)
if vision_config is None:
vision_config = {'architectures': ['InternVisionModel']}
logger.info('vision_config is None. Initializing the InternVisionConfig with default values.')
if llm_config is None:
llm_config = {'architectures': ['Qwen2ForCausalLM']}
logger.info('llm_config is None. Initializing the LlamaConfig config with default values (`LlamaConfig`).')
assert 'architectures' in llm_config, "Should specify architecture in llm_config"
if isinstance(vision_config, dict):
self.vision_config = InternVisionConfig(**vision_config)
else:
self.vision_config = vision_config
if isinstance(llm_config, dict):
architecture: str = llm_config['architectures'][0]
if architecture == 'LlamaForCausalLM':
from transformers import LlamaConfig
self.llm_config = LlamaConfig(**llm_config)
elif architecture == 'Qwen2ForCausalLM':
from transformers import Qwen2Config
self.llm_config = Qwen2Config(**llm_config)
elif architecture == 'Qwen3MoeForCausalLM':
from transformers import Qwen3MoeConfig
self.llm_config = Qwen3MoeConfig(**llm_config)
elif architecture == 'Qwen3ForCausalLM':
from transformers import Qwen3Config
self.llm_config = Qwen3Config(**llm_config)
else:
raise ValueError('Unsupported architecture: {}'.format(architecture))
else:
self.llm_config = llm_config
self.use_backbone_lora = use_backbone_lora
self.use_llm_lora = use_llm_lora
self.select_layer = select_layer
self.force_image_size = force_image_size
self.downsample_ratio = downsample_ratio
self.template = template
self.dynamic_image_size = dynamic_image_size
self.use_thumbnail = use_thumbnail
self.ps_version = ps_version # pixel shuffle version
self.min_dynamic_patch = min_dynamic_patch
self.max_dynamic_patch = max_dynamic_patch
self.tie_word_embeddings = self.llm_config.tie_word_embeddings
logger.info(f'vision_select_layer: {self.select_layer}')
logger.info(f'ps_version: {self.ps_version}')
logger.info(f'min_dynamic_patch: {self.min_dynamic_patch}')
logger.info(f'max_dynamic_patch: {self.max_dynamic_patch}')
def to_dict(self):
"""
Serializes this instance to a Python dictionary. Override the default [`~PretrainedConfig.to_dict`].
Returns:
`Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance,
"""
output = copy.deepcopy(self.__dict__)
output['vision_config'] = self.vision_config.to_dict()
output['llm_config'] = self.llm_config.to_dict()
output['model_type'] = self.__class__.model_type
output['use_backbone_lora'] = self.use_backbone_lora
output['use_llm_lora'] = self.use_llm_lora
output['select_layer'] = self.select_layer
output['force_image_size'] = self.force_image_size
output['downsample_ratio'] = self.downsample_ratio
output['template'] = self.template
output['dynamic_image_size'] = self.dynamic_image_size
output['use_thumbnail'] = self.use_thumbnail
output['ps_version'] = self.ps_version
output['min_dynamic_patch'] = self.min_dynamic_patch
output['max_dynamic_patch'] = self.max_dynamic_patch
return output

391
conversation.py Normal file
View File

@@ -0,0 +1,391 @@
"""
Conversation prompt templates.
We kindly request that you import fastchat instead of copying this file if you wish to use it.
If you have changes in mind, please contribute back so the community can benefit collectively and continue to maintain these valuable templates.
Modified from https://github.com/lm-sys/FastChat/blob/main/fastchat/conversation.py
"""
import dataclasses
from enum import IntEnum, auto
from typing import Dict, List, Tuple, Union
class SeparatorStyle(IntEnum):
"""Separator styles."""
ADD_COLON_SINGLE = auto()
ADD_COLON_TWO = auto()
ADD_COLON_SPACE_SINGLE = auto()
NO_COLON_SINGLE = auto()
NO_COLON_TWO = auto()
ADD_NEW_LINE_SINGLE = auto()
LLAMA2 = auto()
CHATGLM = auto()
CHATML = auto()
CHATINTERN = auto()
DOLLY = auto()
RWKV = auto()
PHOENIX = auto()
ROBIN = auto()
FALCON_CHAT = auto()
CHATGLM3 = auto()
INTERNVL_ZH = auto()
MPT = auto()
@dataclasses.dataclass
class Conversation:
"""A class that manages prompt templates and keeps all conversation history."""
# The name of this template
name: str
# The template of the system prompt
system_template: str = '{system_message}'
# The system message
system_message: str = ''
# The names of two roles
roles: Tuple[str] = ('USER', 'ASSISTANT')
# All messages. Each item is (role, message).
messages: List[List[str]] = ()
# The number of few shot examples
offset: int = 0
# The separator style and configurations
sep_style: SeparatorStyle = SeparatorStyle.ADD_COLON_SINGLE
sep: str = '\n'
sep2: str = None
# Stop criteria (the default one is EOS token)
stop_str: Union[str, List[str]] = None
# Stops generation if meeting any token in this list
stop_token_ids: List[int] = None
def get_prompt(self) -> str:
"""Get the prompt for generation."""
system_prompt = self.system_template.format(system_message=self.system_message)
if self.sep_style == SeparatorStyle.ADD_COLON_SINGLE:
ret = system_prompt + self.sep
for role, message in self.messages:
if message:
ret += role + ': ' + message + self.sep
else:
ret += role + ':'
return ret
elif self.sep_style == SeparatorStyle.ADD_COLON_TWO:
seps = [self.sep, self.sep2]
ret = system_prompt + seps[0]
for i, (role, message) in enumerate(self.messages):
if message:
ret += role + ': ' + message + seps[i % 2]
else:
ret += role + ':'
return ret
elif self.sep_style == SeparatorStyle.ADD_COLON_SPACE_SINGLE:
ret = system_prompt + self.sep
for role, message in self.messages:
if message:
ret += role + ': ' + message + self.sep
else:
ret += role + ': ' # must be end with a space
return ret
elif self.sep_style == SeparatorStyle.ADD_NEW_LINE_SINGLE:
ret = '' if system_prompt == '' else system_prompt + self.sep
for role, message in self.messages:
if message:
ret += role + '\n' + message + self.sep
else:
ret += role + '\n'
return ret
elif self.sep_style == SeparatorStyle.NO_COLON_SINGLE:
ret = system_prompt
for role, message in self.messages:
if message:
ret += role + message + self.sep
else:
ret += role
return ret
elif self.sep_style == SeparatorStyle.NO_COLON_TWO:
seps = [self.sep, self.sep2]
ret = system_prompt
for i, (role, message) in enumerate(self.messages):
if message:
ret += role + message + seps[i % 2]
else:
ret += role
return ret
elif self.sep_style == SeparatorStyle.RWKV:
ret = system_prompt
for i, (role, message) in enumerate(self.messages):
if message:
ret += (
role
+ ': '
+ message.replace('\r\n', '\n').replace('\n\n', '\n')
)
ret += '\n\n'
else:
ret += role + ':'
return ret
elif self.sep_style == SeparatorStyle.LLAMA2:
seps = [self.sep, self.sep2]
if self.system_message:
ret = system_prompt
else:
ret = '[INST] '
for i, (role, message) in enumerate(self.messages):
tag = self.roles[i % 2]
if message:
if i == 0:
ret += message + ' '
else:
ret += tag + ' ' + message + seps[i % 2]
else:
ret += tag
return ret
elif self.sep_style == SeparatorStyle.CHATGLM:
# source: https://huggingface.co/THUDM/chatglm-6b/blob/1d240ba371910e9282298d4592532d7f0f3e9f3e/modeling_chatglm.py#L1302-L1308
# source2: https://huggingface.co/THUDM/chatglm2-6b/blob/e186c891cf64310ac66ef10a87e6635fa6c2a579/modeling_chatglm.py#L926
round_add_n = 1 if self.name == 'chatglm2' else 0
if system_prompt:
ret = system_prompt + self.sep
else:
ret = ''
for i, (role, message) in enumerate(self.messages):
if i % 2 == 0:
ret += f'[Round {i//2 + round_add_n}]{self.sep}'
if message:
ret += f'{role}：{message}{self.sep}'
else:
ret += f'{role}：'
return ret
elif self.sep_style == SeparatorStyle.CHATML:
ret = '' if system_prompt == '' else system_prompt + self.sep + '\n'
for role, message in self.messages:
if message:
ret += role + '\n' + message + self.sep + '\n'
else:
ret += role + '\n'
return ret
elif self.sep_style == SeparatorStyle.CHATGLM3:
ret = ''
if self.system_message:
ret += system_prompt
for role, message in self.messages:
if message:
ret += role + '\n' + ' ' + message
else:
ret += role
return ret
elif self.sep_style == SeparatorStyle.CHATINTERN:
# source: https://huggingface.co/internlm/internlm-chat-7b-8k/blob/bd546fa984b4b0b86958f56bf37f94aa75ab8831/modeling_internlm.py#L771
seps = [self.sep, self.sep2]
ret = system_prompt
for i, (role, message) in enumerate(self.messages):
# if i % 2 == 0:
# ret += "<s>"
if message:
ret += role + ':' + message + seps[i % 2] + '\n'
else:
ret += role + ':'
return ret
elif self.sep_style == SeparatorStyle.DOLLY:
seps = [self.sep, self.sep2]
ret = system_prompt
for i, (role, message) in enumerate(self.messages):
if message:
ret += role + ':\n' + message + seps[i % 2]
if i % 2 == 1:
ret += '\n\n'
else:
ret += role + ':\n'
return ret
elif self.sep_style == SeparatorStyle.PHOENIX:
ret = system_prompt
for role, message in self.messages:
if message:
ret += role + ': ' + '<s>' + message + '</s>'
else:
ret += role + ': ' + '<s>'
return ret
elif self.sep_style == SeparatorStyle.ROBIN:
ret = system_prompt + self.sep
for role, message in self.messages:
if message:
ret += role + ':\n' + message + self.sep
else:
ret += role + ':\n'
return ret
elif self.sep_style == SeparatorStyle.FALCON_CHAT:
ret = ''
if self.system_message:
ret += system_prompt + self.sep
for role, message in self.messages:
if message:
ret += role + ': ' + message + self.sep
else:
ret += role + ':'
return ret
elif self.sep_style == SeparatorStyle.INTERNVL_ZH:
seps = [self.sep, self.sep2]
ret = self.system_message + seps[0]
for i, (role, message) in enumerate(self.messages):
if message:
ret += role + ': ' + message + seps[i % 2]
else:
ret += role + ':'
return ret
elif self.sep_style == SeparatorStyle.MPT:
ret = system_prompt + self.sep
for role, message in self.messages:
if message:
if type(message) is tuple:
message, _, _ = message
ret += role + message + self.sep
else:
ret += role
return ret
else:
raise ValueError(f'Invalid style: {self.sep_style}')
def set_system_message(self, system_message: str):
"""Set the system message."""
self.system_message = system_message
def append_message(self, role: str, message: str):
"""Append a new message."""
self.messages.append([role, message])
def update_last_message(self, message: str):
"""Update the last output.
The last message is typically set to be None when constructing the prompt,
so we need to update it in-place after getting the response from a model.
"""
self.messages[-1][1] = message
def to_gradio_chatbot(self):
"""Convert the conversation to gradio chatbot format."""
ret = []
for i, (role, msg) in enumerate(self.messages[self.offset :]):
if i % 2 == 0:
ret.append([msg, None])
else:
ret[-1][-1] = msg
return ret
def to_openai_api_messages(self):
"""Convert the conversation to OpenAI chat completion format."""
ret = [{'role': 'system', 'content': self.system_message}]
for i, (_, msg) in enumerate(self.messages[self.offset :]):
if i % 2 == 0:
ret.append({'role': 'user', 'content': msg})
else:
if msg is not None:
ret.append({'role': 'assistant', 'content': msg})
return ret
def copy(self):
return Conversation(
name=self.name,
system_template=self.system_template,
system_message=self.system_message,
roles=self.roles,
messages=[[x, y] for x, y in self.messages],
offset=self.offset,
sep_style=self.sep_style,
sep=self.sep,
sep2=self.sep2,
stop_str=self.stop_str,
stop_token_ids=self.stop_token_ids,
)
def dict(self):
return {
'template_name': self.name,
'system_message': self.system_message,
'roles': self.roles,
'messages': self.messages,
'offset': self.offset,
}
# A global registry for all conversation templates
conv_templates: Dict[str, Conversation] = {}
def register_conv_template(template: Conversation, override: bool = False):
"""Register a new conversation template."""
if not override:
assert (
template.name not in conv_templates
), f'{template.name} has been registered.'
conv_templates[template.name] = template
def get_conv_template(name: str) -> Conversation:
"""Get a conversation template."""
return conv_templates[name].copy()
# Both Hermes-2 and internlm2-chat are chatml-format conversation templates. The difference
# is that during training, the preprocessing function for the Hermes-2 template doesn't add
# <s> at the beginning of the tokenized sequence, while the internlm2-chat template does.
# Therefore, they are completely equivalent during inference.
register_conv_template(
Conversation(
name='Hermes-2',
system_template='<|im_start|>system\n{system_message}',
# note: The new system prompt was not used here to avoid changes in benchmark performance.
# system_message='我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
system_message='你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型，英文名叫InternVL, 是一个有用无害的人工智能助手。',
roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
sep_style=SeparatorStyle.MPT,
sep='<|im_end|>',
stop_str='<|endoftext|>',
)
)
register_conv_template(
Conversation(
name='internlm2-chat',
system_template='<|im_start|>system\n{system_message}',
# note: The new system prompt was not used here to avoid changes in benchmark performance.
# system_message='我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
system_message='你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型，英文名叫InternVL, 是一个有用无害的人工智能助手。',
roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
sep_style=SeparatorStyle.MPT,
sep='<|im_end|>',
)
)
register_conv_template(
Conversation(
name='phi3-chat',
system_template='<|system|>\n{system_message}',
# note: The new system prompt was not used here to avoid changes in benchmark performance.
# system_message='我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
system_message='你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型，英文名叫InternVL, 是一个有用无害的人工智能助手。',
roles=('<|user|>\n', '<|assistant|>\n'),
sep_style=SeparatorStyle.MPT,
sep='<|end|>',
)
)
register_conv_template(
Conversation(
name='internvl2_5',
system_template='<|im_start|>system\n{system_message}',
system_message='你是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
sep_style=SeparatorStyle.MPT,
sep='<|im_end|>\n',
)
)

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"eos_token_id": [
151645
],
"transformers_version": "4.56.1"
}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1a6af56d1c56ce86652e2bcd75a1abb042ab547f997608dbc5858ae227018cbb
size 2121876280

433
modeling_intern_vit.py Normal file
View File

@@ -0,0 +1,433 @@
# --------------------------------------------------------
# InternVL
# Copyright (c) 2024 OpenGVLab
# Licensed under The MIT License [see LICENSE for details]
# --------------------------------------------------------
from typing import Optional, Tuple, Union
import torch
import torch.nn.functional as F
import torch.utils.checkpoint
from einops import rearrange
from timm.layers import DropPath
from torch import nn
from transformers.activations import ACT2FN
from transformers.modeling_outputs import (BaseModelOutput,
BaseModelOutputWithPooling)
from transformers.modeling_utils import PreTrainedModel
from transformers.utils import logging
from .configuration_intern_vit import InternVisionConfig
try:
from flash_attn.bert_padding import pad_input, unpad_input
from flash_attn.flash_attn_interface import \
flash_attn_varlen_qkvpacked_func
has_flash_attn = True
except:
print('FlashAttention2 is not installed.')
has_flash_attn = False
logger = logging.get_logger(__name__)
class FlashAttention(nn.Module):
"""Implement the scaled dot product attention with softmax.
Arguments
---------
softmax_scale: The temperature to use for the softmax attention.
(default: 1/sqrt(d_keys) where d_keys is computed at
runtime)
attention_dropout: The dropout rate to apply to the attention
(default: 0.0)
"""
def __init__(self, softmax_scale=None, attention_dropout=0.0, device=None, dtype=None):
super().__init__()
self.softmax_scale = softmax_scale
self.dropout_p = attention_dropout
def forward(self, qkv, key_padding_mask=None, causal=False, cu_seqlens=None,
max_s=None, need_weights=False):
"""Implements the multihead softmax attention.
Arguments
---------
qkv: The tensor containing the query, key, and value. (B, S, 3, H, D) if key_padding_mask is None
if unpadded: (nnz, 3, h, d)
key_padding_mask: a bool tensor of shape (B, S)
"""
assert not need_weights
assert qkv.dtype in [torch.float16, torch.bfloat16]
assert qkv.is_cuda
if cu_seqlens is None:
batch_size = qkv.shape[0]
seqlen = qkv.shape[1]
if key_padding_mask is None:
qkv = rearrange(qkv, 'b s ... -> (b s) ...')
max_s = seqlen
cu_seqlens = torch.arange(0, (batch_size + 1) * seqlen, step=seqlen, dtype=torch.int32,
device=qkv.device)
output = flash_attn_varlen_qkvpacked_func(
qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
softmax_scale=self.softmax_scale, causal=causal
)
output = rearrange(output, '(b s) ... -> b s ...', b=batch_size)
else:
nheads = qkv.shape[-2]
x = rearrange(qkv, 'b s three h d -> b s (three h d)')
x_unpad, indices, cu_seqlens, max_s = unpad_input(x, key_padding_mask)
x_unpad = rearrange(x_unpad, 'nnz (three h d) -> nnz three h d', three=3, h=nheads)
output_unpad = flash_attn_varlen_qkvpacked_func(
x_unpad, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
softmax_scale=self.softmax_scale, causal=causal
)
output = rearrange(pad_input(rearrange(output_unpad, 'nnz h d -> nnz (h d)'),
indices, batch_size, seqlen),
'b s (h d) -> b s h d', h=nheads)
else:
assert max_s is not None
output = flash_attn_varlen_qkvpacked_func(
qkv, cu_seqlens, max_s, self.dropout_p if self.training else 0.0,
softmax_scale=self.softmax_scale, causal=causal
)
return output, None
class InternRMSNorm(nn.Module):
def __init__(self, hidden_size, eps=1e-6):
super().__init__()
self.weight = nn.Parameter(torch.ones(hidden_size))
self.variance_epsilon = eps
def forward(self, hidden_states):
input_dtype = hidden_states.dtype
hidden_states = hidden_states.to(torch.float32)
variance = hidden_states.pow(2).mean(-1, keepdim=True)
hidden_states = hidden_states * torch.rsqrt(variance + self.variance_epsilon)
return self.weight * hidden_states.to(input_dtype)
try:
from apex.normalization import FusedRMSNorm
InternRMSNorm = FusedRMSNorm # noqa
logger.info('Discovered apex.normalization.FusedRMSNorm - will use it instead of InternRMSNorm')
except ImportError:
# using the normal InternRMSNorm
pass
except Exception:
logger.warning('discovered apex but it failed to load, falling back to InternRMSNorm')
pass
NORM2FN = {
'rms_norm': InternRMSNorm,
'layer_norm': nn.LayerNorm,
}
class InternVisionEmbeddings(nn.Module):
def __init__(self, config: InternVisionConfig):
super().__init__()
self.config = config
self.embed_dim = config.hidden_size
self.image_size = config.image_size
self.patch_size = config.patch_size
self.class_embedding = nn.Parameter(
torch.randn(1, 1, self.embed_dim),
)
self.patch_embedding = nn.Conv2d(
in_channels=3, out_channels=self.embed_dim, kernel_size=self.patch_size, stride=self.patch_size
)
self.num_patches = (self.image_size // self.patch_size) ** 2
self.num_positions = self.num_patches + 1
self.position_embedding = nn.Parameter(torch.randn(1, self.num_positions, self.embed_dim))
def _get_pos_embed(self, pos_embed, H, W):
target_dtype = pos_embed.dtype
pos_embed = pos_embed.float().reshape(
1, self.image_size // self.patch_size, self.image_size // self.patch_size, -1).permute(0, 3, 1, 2)
pos_embed = F.interpolate(pos_embed, size=(H, W), mode='bicubic', align_corners=False). \
reshape(1, -1, H * W).permute(0, 2, 1).to(target_dtype)
return pos_embed
def forward(self, pixel_values: torch.FloatTensor) -> torch.Tensor:
target_dtype = self.patch_embedding.weight.dtype
patch_embeds = self.patch_embedding(pixel_values) # shape = [*, channel, width, height]
batch_size, _, height, width = patch_embeds.shape
patch_embeds = patch_embeds.flatten(2).transpose(1, 2)
class_embeds = self.class_embedding.expand(batch_size, 1, -1).to(target_dtype)
embeddings = torch.cat([class_embeds, patch_embeds], dim=1)
position_embedding = torch.cat([
self.position_embedding[:, :1, :],
self._get_pos_embed(self.position_embedding[:, 1:, :], height, width)
], dim=1)
embeddings = embeddings + position_embedding.to(target_dtype)
return embeddings
class InternAttention(nn.Module):
"""Multi-headed attention from 'Attention Is All You Need' paper"""
def __init__(self, config: InternVisionConfig):
super().__init__()
self.config = config
self.embed_dim = config.hidden_size
self.num_heads = config.num_attention_heads
self.use_flash_attn = config.use_flash_attn and has_flash_attn
if config.use_flash_attn and not has_flash_attn:
print('Warning: Flash Attention is not available, use_flash_attn is set to False.')
self.head_dim = self.embed_dim // self.num_heads
if self.head_dim * self.num_heads != self.embed_dim:
raise ValueError(
f'embed_dim must be divisible by num_heads (got `embed_dim`: {self.embed_dim} and `num_heads`:'
f' {self.num_heads}).'
)
self.scale = self.head_dim ** -0.5
self.qkv = nn.Linear(self.embed_dim, 3 * self.embed_dim, bias=config.qkv_bias)
self.attn_drop = nn.Dropout(config.attention_dropout)
self.proj_drop = nn.Dropout(config.dropout)
self.qk_normalization = config.qk_normalization
if self.qk_normalization:
self.q_norm = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
self.k_norm = InternRMSNorm(self.embed_dim, eps=config.layer_norm_eps)
if self.use_flash_attn:
self.inner_attn = FlashAttention(attention_dropout=config.attention_dropout)
self.proj = nn.Linear(self.embed_dim, self.embed_dim)
def _naive_attn(self, x):
B, N, C = x.shape
qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
q, k, v = qkv.unbind(0) # make torchscript happy (cannot use tensor as tuple)
if self.qk_normalization:
B_, H_, N_, D_ = q.shape
q = self.q_norm(q.transpose(1, 2).flatten(-2, -1)).view(B_, N_, H_, D_).transpose(1, 2)
k = self.k_norm(k.transpose(1, 2).flatten(-2, -1)).view(B_, N_, H_, D_).transpose(1, 2)
attn = ((q * self.scale) @ k.transpose(-2, -1))
attn = attn.softmax(dim=-1)
attn = self.attn_drop(attn)
x = (attn @ v).transpose(1, 2).reshape(B, N, C)
x = self.proj(x)
x = self.proj_drop(x)
return x
def _flash_attn(self, x, key_padding_mask=None, need_weights=False):
qkv = self.qkv(x)
qkv = rearrange(qkv, 'b s (three h d) -> b s three h d', three=3, h=self.num_heads)
if self.qk_normalization:
q, k, v = qkv.unbind(2)
q = self.q_norm(q.flatten(-2, -1)).view(q.shape)
k = self.k_norm(k.flatten(-2, -1)).view(k.shape)
qkv = torch.stack([q, k, v], dim=2)
context, _ = self.inner_attn(
qkv, key_padding_mask=key_padding_mask, need_weights=need_weights, causal=False
)
outs = self.proj(rearrange(context, 'b s h d -> b s (h d)'))
outs = self.proj_drop(outs)
return outs
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
x = self._naive_attn(hidden_states) if not self.use_flash_attn else self._flash_attn(hidden_states)
return x
class InternMLP(nn.Module):
def __init__(self, config: InternVisionConfig):
super().__init__()
self.config = config
self.act = ACT2FN[config.hidden_act]
self.fc1 = nn.Linear(config.hidden_size, config.intermediate_size)
self.fc2 = nn.Linear(config.intermediate_size, config.hidden_size)
def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
hidden_states = self.fc1(hidden_states)
hidden_states = self.act(hidden_states)
hidden_states = self.fc2(hidden_states)
return hidden_states
class InternVisionEncoderLayer(nn.Module):
def __init__(self, config: InternVisionConfig, drop_path_rate: float):
super().__init__()
self.embed_dim = config.hidden_size
self.intermediate_size = config.intermediate_size
self.norm_type = config.norm_type
self.attn = InternAttention(config)
self.mlp = InternMLP(config)
self.norm1 = NORM2FN[self.norm_type](self.embed_dim, eps=config.layer_norm_eps)
self.norm2 = NORM2FN[self.norm_type](self.embed_dim, eps=config.layer_norm_eps)
self.ls1 = nn.Parameter(config.initializer_factor * torch.ones(self.embed_dim))
self.ls2 = nn.Parameter(config.initializer_factor * torch.ones(self.embed_dim))
self.drop_path1 = DropPath(drop_path_rate) if drop_path_rate > 0. else nn.Identity()
self.drop_path2 = DropPath(drop_path_rate) if drop_path_rate > 0. else nn.Identity()
def forward(
self,
hidden_states: torch.Tensor,
) -> Tuple[torch.FloatTensor, Optional[torch.FloatTensor], Optional[Tuple[torch.FloatTensor]]]:
"""
Args:
hidden_states (`Tuple[torch.FloatTensor, Optional[torch.FloatTensor]]`): input to the layer of shape `(batch, seq_len, embed_dim)`
"""
hidden_states = hidden_states + self.drop_path1(self.attn(self.norm1(hidden_states).to(hidden_states.dtype)) * self.ls1)
hidden_states = hidden_states + self.drop_path2(self.mlp(self.norm2(hidden_states).to(hidden_states.dtype)) * self.ls2)
return hidden_states
class InternVisionEncoder(nn.Module):
"""
Transformer encoder consisting of `config.num_hidden_layers` self attention layers. Each layer is a
[`InternEncoderLayer`].
Args:
config (`InternConfig`):
The corresponding vision configuration for the `InternEncoder`.
"""
def __init__(self, config: InternVisionConfig):
super().__init__()
self.config = config
# stochastic depth decay rule
dpr = [x.item() for x in torch.linspace(0, config.drop_path_rate, config.num_hidden_layers)]
self.layers = nn.ModuleList([
InternVisionEncoderLayer(config, dpr[idx]) for idx in range(config.num_hidden_layers)])
self.gradient_checkpointing = True
def forward(
self,
inputs_embeds,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
) -> Union[Tuple, BaseModelOutput]:
r"""
Args:
inputs_embeds (`torch.FloatTensor` of shape `(batch_size, sequence_length, hidden_size)`):
Embedded representation of the inputs. Should be float, not int tokens.
output_hidden_states (`bool`, *optional*):
Whether or not to return the hidden states of all layers. See `hidden_states` under returned tensors
for more detail.
return_dict (`bool`, *optional*):
Whether or not to return a [`~utils.ModelOutput`] instead of a plain tuple.
"""
output_hidden_states = (
output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
)
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
encoder_states = () if output_hidden_states else None
hidden_states = inputs_embeds
for idx, encoder_layer in enumerate(self.layers):
if output_hidden_states:
encoder_states = encoder_states + (hidden_states,)
if self.gradient_checkpointing and self.training:
layer_outputs = torch.utils.checkpoint.checkpoint(
encoder_layer,
hidden_states)
else:
layer_outputs = encoder_layer(
hidden_states,
)
hidden_states = layer_outputs
if output_hidden_states:
encoder_states = encoder_states + (hidden_states,)
if not return_dict:
return tuple(v for v in [hidden_states, encoder_states] if v is not None)
return BaseModelOutput(
last_hidden_state=hidden_states, hidden_states=encoder_states
)
class InternVisionModel(PreTrainedModel):
main_input_name = 'pixel_values'
_supports_flash_attn_2 = True
supports_gradient_checkpointing = True
config_class = InternVisionConfig
_no_split_modules = ['InternVisionEncoderLayer']
# support transformers 4.51.+
_tp_plan = ''
def __init__(self, config: InternVisionConfig):
super().__init__(config)
self.config = config
self.embeddings = InternVisionEmbeddings(config)
self.encoder = InternVisionEncoder(config)
def resize_pos_embeddings(self, old_size, new_size, patch_size):
pos_emb = self.embeddings.position_embedding
_, num_positions, embed_dim = pos_emb.shape
cls_emb = pos_emb[:, :1, :]
pos_emb = pos_emb[:, 1:, :].reshape(1, old_size // patch_size, old_size // patch_size, -1).permute(0, 3, 1, 2)
pos_emb = F.interpolate(pos_emb.float(), size=new_size // patch_size, mode='bicubic', align_corners=False)
pos_emb = pos_emb.to(cls_emb.dtype).reshape(1, embed_dim, -1).permute(0, 2, 1)
pos_emb = torch.cat([cls_emb, pos_emb], dim=1)
self.embeddings.position_embedding = nn.Parameter(pos_emb)
self.embeddings.image_size = new_size
logger.info('Resized position embeddings from {} to {}'.format(old_size, new_size))
def get_input_embeddings(self):
return self.embeddings
def forward(
self,
pixel_values: Optional[torch.FloatTensor] = None,
output_hidden_states: Optional[bool] = None,
return_dict: Optional[bool] = None,
pixel_embeds: Optional[torch.FloatTensor] = None,
) -> Union[Tuple, BaseModelOutputWithPooling]:
output_hidden_states = (
output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
)
return_dict = return_dict if return_dict is not None else self.config.use_return_dict
if pixel_values is None and pixel_embeds is None:
raise ValueError('You have to specify pixel_values or pixel_embeds')
if pixel_embeds is not None:
hidden_states = pixel_embeds
else:
if len(pixel_values.shape) == 4:
hidden_states = self.embeddings(pixel_values)
else:
raise ValueError(f'wrong pixel_values size: {pixel_values.shape}')
encoder_outputs = self.encoder(
inputs_embeds=hidden_states,
output_hidden_states=output_hidden_states,
return_dict=return_dict,
)
last_hidden_state = encoder_outputs.last_hidden_state
pooled_output = last_hidden_state[:, 0, :]
if not return_dict:
return (last_hidden_state, pooled_output) + encoder_outputs[1:]
return BaseModelOutputWithPooling(
last_hidden_state=last_hidden_state,
pooler_output=pooled_output,
hidden_states=encoder_outputs.hidden_states,
attentions=encoder_outputs.attentions,
)

376
modeling_internvl_chat.py Normal file
View File

@@ -0,0 +1,376 @@
# --------------------------------------------------------
# InternVL
# Copyright (c) 2024 OpenGVLab
# Licensed under The MIT License [see LICENSE for details]
# --------------------------------------------------------
import warnings
from typing import List, Optional, Tuple, Union
import torch.utils.checkpoint
import transformers
from torch import nn
from torch.nn import CrossEntropyLoss
from transformers import GenerationConfig
from transformers.modeling_outputs import CausalLMOutputWithPast
from transformers.modeling_utils import PreTrainedModel
from transformers.utils import logging
from transformers import LlamaForCausalLM, Qwen2ForCausalLM, Qwen3ForCausalLM, Qwen3MoeForCausalLM
from .configuration_internvl_chat import InternVLChatConfig
from .conversation import get_conv_template
from .modeling_intern_vit import InternVisionModel, has_flash_attn
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
supports_gradient_checkpointing = True
_no_split_modules = [
"InternVisionModel",
"Qwen3DecoderLayer",
]
# support transformers 4.51.+
_tp_plan = ''
def __init__(self, config: InternVLChatConfig, vision_model=None, language_model=None, use_flash_attn=True):
super().__init__(config)
assert version_cmp(transformers.__version__, '4.37.0', '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:
architecture: str = config.llm_config.architectures[0]
if architecture == 'LlamaForCausalLM':
self.language_model = LlamaForCausalLM(config.llm_config)
elif architecture == 'Qwen2ForCausalLM':
self.language_model = Qwen2ForCausalLM(config.llm_config)
elif architecture == 'Qwen3MoeForCausalLM':
self.language_model = Qwen3MoeForCausalLM(config.llm_config)
elif architecture == 'Qwen3ForCausalLM':
self.language_model = Qwen3ForCausalLM(config.llm_config)
else:
raise NotImplementedError(f'{architecture} 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.is_initialized() and 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 = min(selected.sum(), vit_embeds.size(0))
input_embeds[selected][:n_token] = input_embeds[selected][:n_token] * 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.strip())
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.strip())[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.strip())
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.strip())[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,
**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,
use_cache=True,
**generate_kwargs,
)
return outputs
@property
def lm_head(self):
return self.language_model.get_output_embeddings()
def get_output_embeddings(self):
return self.language_model.get_output_embeddings()
def get_input_embeddings(self):
return self.language_model.get_input_embeddings()
def set_input_embeddings(self, value):
return self.language_model.set_input_embeddings(value)
def set_output_embeddings(self, value):
return self.language_model.set_output_embeddings(value)

34
preprocessor_config.json Normal file
View File

@@ -0,0 +1,34 @@
{
"crop_size": null,
"crop_to_patches": false,
"data_format": "channels_first",
"default_to_square": true,
"device": null,
"do_center_crop": null,
"do_convert_rgb": true,
"do_normalize": true,
"do_rescale": true,
"do_resize": true,
"image_mean": [
0.485,
0.456,
0.406
],
"image_processor_type": "GotOcr2ImageProcessorFast",
"image_std": [
0.229,
0.224,
0.225
],
"input_data_format": null,
"max_patches": 12,
"min_patches": 1,
"processor_class": "InternVLProcessor",
"resample": 3,
"rescale_factor": 0.00392156862745098,
"return_tensors": null,
"size": {
"height": 448,
"width": 448
}
}

40
special_tokens_map.json Normal file
View File

@@ -0,0 +1,40 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>",
"<img>",
"</img>",
"<IMG_CONTEXT>",
"<quad>",
"</quad>",
"<ref>",
"</ref>",
"<box>",
"</box>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

757561
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

322
tokenizer_config.json Normal file
View File

@@ -0,0 +1,322 @@
{
"add_bos_token": false,
"add_eos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "<tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "</tool_response>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "<think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151668": {
"content": "</think>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151669": {
"content": "<img>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151670": {
"content": "</img>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151671": {
"content": "<IMG_CONTEXT>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151672": {
"content": "<quad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151673": {
"content": "</quad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151674": {
"content": "<ref>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151675": {
"content": "</ref>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151676": {
"content": "<box>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151677": {
"content": "</box>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>",
"<img>",
"</img>",
"<IMG_CONTEXT>",
"<quad>",
"</quad>",
"<ref>",
"</ref>",
"<box>",
"</box>"
],
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 14588,
"pad_token": "<|endoftext|>",
"processor_class": "InternVLProcessor",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long