add patch processor func

Former-commit-id: 0cd6327da6a044b4a62f203a662e5bb6068d9c29

src/llamafactory/model/patcher.py

@@ -34,11 +34,17 @@ from .model_utils.packing import configure_packing
 from .model_utils.quantization import configure_quantization
 from .model_utils.rope import configure_rope
 from .model_utils.valuehead import prepare_valuehead_model
-from .model_utils.visual import autocast_projector_dtype, configure_visual_model
+from .model_utils.visual import (
+    autocast_projector_dtype,
+    configure_visual_model,
+    get_image_seqlen,
+    get_patch_size,
+    get_vision_feature_select_strategy,
+)
 
 
 if TYPE_CHECKING:
-    from transformers import PretrainedConfig, PreTrainedTokenizer
+    from transformers import PretrainedConfig, PreTrainedTokenizer, ProcessorMixin
     from trl import AutoModelForCausalLMWithValueHead
 
     from ..hparams import ModelArguments
@@ -52,6 +58,22 @@ def patch_tokenizer(tokenizer: "PreTrainedTokenizer") -> None:
         tokenizer._pad = MethodType(PreTrainedTokenizerBase._pad, tokenizer)
 
 
+def patch_processor(
+    processor: "ProcessorMixin",
+    config: "PretrainedConfig",
+    tokenizer: "PreTrainedTokenizer",
+    model_args: "ModelArguments",
+) -> None:
+    setattr(processor, "tokenizer", tokenizer)
+    setattr(processor, "image_seqlen", get_image_seqlen(config))
+    setattr(processor, "image_resolution", model_args.image_resolution)
+    setattr(processor, "patch_size", get_patch_size(config))
+    setattr(processor, "video_resolution", model_args.video_resolution)
+    setattr(processor, "video_fps", model_args.video_fps)
+    setattr(processor, "video_maxlen", model_args.video_maxlen)
+    setattr(processor, "vision_feature_select_strategy", get_vision_feature_select_strategy(config))
+
+
 def patch_config(
     config: "PretrainedConfig",
     tokenizer: "PreTrainedTokenizer",