diff --git a/mteb/models/overview.py b/mteb/models/overview.py
index 740405fe97..33f32cd4d1 100644
--- a/mteb/models/overview.py
+++ b/mteb/models/overview.py
@@ -13,6 +13,7 @@
 from mteb.model_meta import ModelMeta
 from mteb.models import (
     align_models,
+    ara_models,
     arctic_models,
     bedrock_models,
     bge_models,
@@ -70,11 +71,11 @@
     stella_models,
     text2vec_models,
     uae_models,
+    vdr_models,
     vista_models,
     vlm2vec_models,
     voyage_models,
     voyage_v,
-    ara_models,
 )
 
 logger = logging.getLogger(__name__)
@@ -141,6 +142,7 @@
     text2vec_models,
     uae_models,
     voyage_models,
+    vdr_models,
     fa_models,
     ara_models,
 ]
diff --git a/mteb/models/vdr_models.py b/mteb/models/vdr_models.py
new file mode 100644
index 0000000000..bc1cd66c83
--- /dev/null
+++ b/mteb/models/vdr_models.py
@@ -0,0 +1,52 @@
+from __future__ import annotations
+
+from functools import partial
+
+from mteb.encoder_interface import PromptType
+from mteb.model_meta import ModelMeta
+from mteb.models.instruct_wrapper import InstructSentenceTransformerWrapper
+
+
+def instruction_template(
+    instruction: str, prompt_type: PromptType | None = None
+) -> str:
+    return "{instruction}"
+
+
+languages = [
+    "eng_Latn",
+    "ita_Latn",
+    "fra_Latn",
+    "deu_Latn",
+    "spa_Latn",
+]
+
+vdr_2b_multi_v1 = ModelMeta(
+    loader=partial(
+        InstructSentenceTransformerWrapper,
+        model_name="llamaindex/vdr-2b-multi-v1",
+        instruction_template=instruction_template,
+        max_seq_length=32768,
+        apply_instruction_to_passages=True,
+    ),
+    name="llamaindex/vdr-2b-multi-v1",
+    languages=languages,
+    open_weights=True,
+    revision="2c4e54c8db4071cc61fc3c62f4490124e40c37db",
+    release_date="2024-01-08",
+    modalities=["text"],  # TODO: integrate with image
+    n_parameters=2_000_000_000,
+    memory_usage_mb=4213,
+    max_tokens=32768,
+    embed_dim=1536,
+    license="apache-2.0",
+    reference="https://huggingface.co/llamaindex/vdr-2b-multi-v1",
+    similarity_fn_name="cosine",
+    framework=["PyTorch", "Sentence Transformers"],
+    use_instructions=True,
+    public_training_code=None,
+    public_training_data="https://huggingface.co/datasets/llamaindex/vdr-multilingual-train",
+    training_datasets={
+        # llamaindex/vdr-multilingual-train
+    },
+)