File size: 3,156 Bytes
8974fb7 | 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 | from typing import Any, Optional
from transformers.configuration_utils import PretrainedConfig
from transformers.models.qwen3 import Qwen3Config
from transformers import Qwen2_5_VLProcessor, AutoProcessor, AutoConfig
class MonkeyOCRv2VisionConfig(PretrainedConfig):
model_type: str = "monkeyocr_vit"
def __init__(
self,
embed_dim: int = 1536, # vision encoder embed size
hidden_size: int = 1536, # after merger hidden size
intermediate_size: int = 4224,
num_hidden_layers: int = 42,
num_attention_heads: int = 12,
num_channels: int = 3,
patch_size: int = 14,
spatial_merge_size: int = 2,
temporal_patch_size: int = 1,
rms_norm_eps: float = 1e-5,
use_bias: bool = False,
attn_implementation="flash_attention_2", # "eager","sdpa","flash_attention_2"
initializer_range=0.02,
init_merger_std=0.02,
is_causal=False, # ve causal forward
post_norm=True,
gradient_checkpointing=False,
**kwargs: Any,
):
super().__init__(**kwargs)
self.embed_dim = embed_dim
self.hidden_size = hidden_size
self.intermediate_size = intermediate_size
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.spatial_merge_size = spatial_merge_size
self.temporal_patch_size = temporal_patch_size
self.rms_norm_eps = rms_norm_eps
self.use_bias = use_bias
self.attn_implementation = attn_implementation
self.initializer_range = initializer_range
self.init_merger_std = init_merger_std
self.is_causal = is_causal
self.post_norm = post_norm
self.gradient_checkpointing = gradient_checkpointing
class MonkeyOCRv2Config(Qwen3Config):
model_type = "monkeyocrv2"
def __init__(self,
image_token_id = 151655,
video_token_id = 151656,
vision_config: Optional[dict] = None, *args, **kwargs):
super().__init__(*args, **kwargs)
self.image_token_id = image_token_id
self.video_token_id = video_token_id
self.vision_config = MonkeyOCRv2VisionConfig(**(vision_config or {}))
def save_pretrained(self, save_directory, **kwargs):
self._auto_class = None
super().save_pretrained(save_directory, **kwargs)
class MonkeyOCRv2Processor(Qwen2_5_VLProcessor):
attributes = ["image_processor", "tokenizer"]
def __init__(self, image_processor=None, tokenizer=None, chat_template=None, **kwargs):
super().__init__(image_processor, tokenizer, chat_template=chat_template)
self.image_token = "<|image_pad|>" if not hasattr(tokenizer, "image_token") else tokenizer.image_token
self.image_token_id = 151655 if not hasattr(tokenizer, "image_token_id") else tokenizer.image_token_id
AutoProcessor.register("monkeyocrv2", MonkeyOCRv2Processor)
AutoConfig.register("monkeyocrv2", MonkeyOCRv2Config)
__all__ = ["MonkeyOCRv2Config", "MonkeyOCRv2VisionConfig", "MonkeyOCRv2Processor"] |