Update README.md

README.md

@@ -28,6 +28,25 @@ from PIL import Image
 import torch
 from transformers import AutoProcessor, AutoModelForVision2Seq
 
+class LlavaMultiModalProjectorYiVL(nn.Module):
+    def __init__(self, config: "LlavaConfig"):
+        super().__init__()
+        self.linear_1 = nn.Linear(config.vision_config.hidden_size, config.text_config.hidden_size, bias=True)
+        self.linear_2 = nn.LayerNorm(config.text_config.hidden_size, bias=True)
+        self.linear_3 = nn.Linear(config.text_config.hidden_size, config.text_config.hidden_size, bias=True)
+        self.linear_4 = nn.LayerNorm(config.text_config.hidden_size, bias=True)
+        self.act = nn.GELU()
+
+    def forward(self, image_features):
+        hidden_states = self.linear_1(image_features)
+        hidden_states = self.linear_2(hidden_states)
+        hidden_states = self.act(hidden_states)
+        hidden_states = self.linear_3(hidden_states)
+        hidden_states = self.linear_4(hidden_states)
+        return hidden_states
+
+transformers.models.llava.modeling_llava.LlavaMultiModalProjector = LlavaMultiModalProjectorYiVL
+
 model_id = "BUAADreamer/Yi-VL-34B-hf"
 
 messages = [