diff --git a/examples/int8_training/fine_tune_blip2_int8.py b/examples/int8_training/fine_tune_blip2_int8.py
index 25121f6..ca6ba40 100644
--- a/examples/int8_training/fine_tune_blip2_int8.py
+++ b/examples/int8_training/fine_tune_blip2_int8.py
@@ -26,7 +26,6 @@ config = LoraConfig(
     lora_alpha=32,
     lora_dropout=0.05,
     bias="none",
-    task_type="VISION_2_SEQ",
 )
 
 # We load our model and processor using `transformers`
diff --git a/src/peft/mapping.py b/src/peft/mapping.py
index 4abbd5a..35a6901 100644
--- a/src/peft/mapping.py
+++ b/src/peft/mapping.py
@@ -19,7 +19,6 @@ from .peft_model import (
     PeftModelForSeq2SeqLM,
     PeftModelForSequenceClassification,
     PeftModelForTokenClassification,
-    PeftModelForVision2Seq,
 )
 from .tuners import LoraConfig, PrefixTuningConfig, PromptEncoderConfig, PromptTuningConfig
 from .utils import PromptLearningConfig
@@ -30,7 +29,6 @@ MODEL_TYPE_TO_PEFT_MODEL_MAPPING = {
     "SEQ_2_SEQ_LM": PeftModelForSeq2SeqLM,
     "CAUSAL_LM": PeftModelForCausalLM,
     "TOKEN_CLS": PeftModelForTokenClassification,
-    "VISION_2_SEQ": PeftModelForVision2Seq,
 }
 
 PEFT_TYPE_TO_CONFIG_MAPPING = {
@@ -140,9 +138,6 @@ def get_peft_model(model, peft_config):
     model_config = model.config.to_dict()
     peft_config.base_model_name_or_path = model.__dict__.get("name_or_path", None)
 
-    if peft_config.task_type == "VISION_2_SEQ" and not isinstance(peft_config, LoraConfig):
-        raise ValueError("Vision2Seq task type is only supported with LORA")
-
     if peft_config.task_type not in MODEL_TYPE_TO_PEFT_MODEL_MAPPING.keys():
         peft_config = _prepare_lora_config(peft_config, model_config)
         return PeftModel(model, peft_config)
diff --git a/src/peft/peft_model.py b/src/peft/peft_model.py
index 6706b23..85757b7 100644
--- a/src/peft/peft_model.py
+++ b/src/peft/peft_model.py
@@ -1034,72 +1034,3 @@ class PeftModelForTokenClassification(PeftModel):
                 hidden_states=outputs.hidden_states,
                 attentions=outputs.attentions,
             )
-
-
-class PeftModelForVision2Seq(PeftModel):
-    """
-    Peft model for vision to text models.
-
-    Args:
-        model ([`~transformers.PreTrainedModel`]): Base transformer model.
-        peft_config ([`PeftConfig`]): Peft config.
-
-
-    Example:
-
-        ```py
-        >>> from transformers import AutoModelForVision2Seq
-        >>> from peft import PeftModelForVision2Seq, get_peft_config
-
-        >>> config = {
-        ...     "peft_type": "LORA",
-        ...     "task_type": "VISION_2_SEQ",
-        ...     "inference_mode": False,
-        ...     "r": 8,
-        ...     "target_modules": ["q", "v"],
-        ...     "lora_alpha": 32,
-        ...     "lora_dropout": 0.1,
-        ...     "merge_weights": False,
-        ...     "fan_in_fan_out": False,
-        ...     "enable_lora": None,
-        ...     "bias": "none",
-        ... }
-
-        >>> peft_config = get_peft_config(config)
-        >>> model = AutoModelForVision2Seq.from_pretrained("Salesforce/blip2-flan-t5-xl")
-        >>> peft_model = PeftModelForVision2Seq(model, peft_config)
-        >>> peft_model.print_trainable_parameters()
-        trainable params: 1843200 || all params: 775873280 || trainable%: 0.23756456724479544
-        ```
-    """
-
-    def __init__(self, model, peft_config: PeftConfig):
-        super().__init__(model, peft_config)
-        self.base_model_prepare_inputs_for_generation = self.base_model.prepare_inputs_for_generation
-
-    def forward(
-        self,
-        pixel_values=None,
-        attention_mask=None,
-        decoder_input_ids=None,
-        decoder_attention_mask=None,
-        labels=None,
-        output_attentions=None,
-        output_hidden_states=None,
-        return_dict=None,
-        **kwargs,
-    ):
-        r"""
-        A simple wrapper around the base model's forward method.
-        """
-        return self.base_model(
-            pixel_values=pixel_values,
-            attention_mask=attention_mask,
-            decoder_input_ids=decoder_input_ids,
-            decoder_attention_mask=decoder_attention_mask,
-            labels=labels,
-            output_attentions=output_attentions,
-            output_hidden_states=output_hidden_states,
-            return_dict=return_dict,
-            **kwargs,
-        )