diff --git a/mteb/models/siglip_models.py b/mteb/models/siglip_models.py
index 739b5aa59a..3bca2e508e 100644
--- a/mteb/models/siglip_models.py
+++ b/mteb/models/siglip_models.py
@@ -155,6 +155,10 @@ def get_fused_embeddings(
             return image_embeddings
 
 
+siglip_training_datasets = {
+    # WebLI https://arxiv.org/abs/2209.06794
+}
+
 siglip_so400m_patch14_224 = ModelMeta(
     loader=partial(
         SiglipModelWrapper,
@@ -165,18 +169,18 @@ def get_fused_embeddings(
     revision="d04cf29fca7b6374f74d8bea1969314492266b5e",
     release_date="2024-01-08",
     modalities=["image", "text"],
-    n_parameters=None,
-    max_tokens=None,
-    embed_dim=None,
-    license=None,
-    open_weights=None,
-    public_training_code=None,
+    n_parameters=877_000_000,
+    max_tokens=16,
+    embed_dim=1152,
+    license="apache-2.0",
+    open_weights=True,
+    public_training_code="https://github.com/google-research/big_vision/blob/main/big_vision/trainers/proj/image_text/siglip.py",
     public_training_data=None,
     framework=["PyTorch"],
-    reference=None,
+    reference="https://huggingface.co/google/siglip-so400m-patch14-224",
     similarity_fn_name=None,
-    use_instructions=None,
-    training_datasets=None,
+    use_instructions=False,
+    training_datasets=siglip_training_datasets,
 )
 
 siglip_so400m_patch14_384 = ModelMeta(
@@ -189,18 +193,18 @@ def get_fused_embeddings(
     revision="9fdffc58afc957d1a03a25b10dba0329ab15c2a3",
     release_date="2024-01-08",
     modalities=["image", "text"],
-    n_parameters=None,
-    max_tokens=None,
-    embed_dim=None,
-    license=None,
-    open_weights=None,
-    public_training_code=None,
+    n_parameters=878_000_000,
+    max_tokens=64,
+    embed_dim=1152,
+    license="apache-2.0",
+    open_weights=True,
+    public_training_code="https://github.com/google-research/big_vision/blob/main/big_vision/trainers/proj/image_text/siglip.py",
     public_training_data=None,
     framework=["PyTorch"],
-    reference=None,
+    reference="https://huggingface.co/google/siglip-so400m-patch14-384",
     similarity_fn_name=None,
-    use_instructions=None,
-    training_datasets=None,
+    use_instructions=False,
+    training_datasets=siglip_training_datasets,
 )
 
 siglip_so400m_patch16_256_i18n = ModelMeta(
@@ -213,18 +217,18 @@ def get_fused_embeddings(
     revision="365d321c0cfdea96bc28e3a29787a11a062681a1",
     release_date="2024-01-08",
     modalities=["image", "text"],
-    n_parameters=None,
-    max_tokens=None,
-    embed_dim=None,
-    license=None,
-    open_weights=None,
-    public_training_code=None,
+    n_parameters=1_130_000_000,
+    max_tokens=64,
+    embed_dim=1152,
+    license="apache-2.0",
+    open_weights=True,
+    public_training_code="https://github.com/google-research/big_vision/blob/main/big_vision/trainers/proj/image_text/siglip.py",
     public_training_data=None,
     framework=["PyTorch"],
-    reference=None,
+    reference="https://huggingface.co/google/siglip-so400m-patch16-256-i18n",
     similarity_fn_name=None,
-    use_instructions=None,
-    training_datasets=None,
+    use_instructions=False,
+    training_datasets=siglip_training_datasets,
 )
 
 siglip_base_patch16_256_multilingual = ModelMeta(
@@ -237,18 +241,18 @@ def get_fused_embeddings(
     revision="8952a4eafcde3cb7ab46b1dd629b33f8784ca9c6",
     release_date="2024-01-08",
     modalities=["image", "text"],
-    n_parameters=None,
-    max_tokens=None,
-    embed_dim=None,
-    license=None,
-    open_weights=None,
-    public_training_code=None,
+    n_parameters=371_000_000,
+    max_tokens=64,
+    embed_dim=768,
+    license="apache-2.0",
+    open_weights=True,
+    public_training_code="https://github.com/google-research/big_vision/blob/main/big_vision/trainers/proj/image_text/siglip.py",
     public_training_data=None,
     framework=["PyTorch"],
-    reference=None,
+    reference="https://huggingface.co/google/siglip-base-patch16-256-multilingual",
     similarity_fn_name=None,
-    use_instructions=None,
-    training_datasets=None,
+    use_instructions=False,
+    training_datasets=siglip_training_datasets,
 )
 
 siglip_base_patch16_256 = ModelMeta(
@@ -261,18 +265,18 @@ def get_fused_embeddings(
     revision="b078df89e446d623010d890864d4207fe6399f61",
     release_date="2024-01-08",
     modalities=["image", "text"],
-    n_parameters=None,
-    max_tokens=None,
-    embed_dim=None,
-    license=None,
-    open_weights=None,
-    public_training_code=None,
+    n_parameters=203_000_000,
+    max_tokens=64,
+    embed_dim=768,
+    license="apache-2.0",
+    open_weights=True,
+    public_training_code="https://github.com/google-research/big_vision/blob/main/big_vision/trainers/proj/image_text/siglip.py",
     public_training_data=None,
     framework=["PyTorch"],
-    reference=None,
+    reference="https://huggingface.co/google/siglip-base-patch16-256",
     similarity_fn_name=None,
-    use_instructions=None,
-    training_datasets=None,
+    use_instructions=False,
+    training_datasets=siglip_training_datasets,
 )
 
 siglip_base_patch16_512 = ModelMeta(
@@ -285,18 +289,18 @@ def get_fused_embeddings(
     revision="753a949581523b60257d93e18391e8c27f72eb22",
     release_date="2024-01-08",
     modalities=["image", "text"],
-    n_parameters=None,
-    max_tokens=None,
-    embed_dim=None,
-    license=None,
-    open_weights=None,
-    public_training_code=None,
+    n_parameters=204_000_000,
+    max_tokens=64,
+    embed_dim=768,
+    license="apache-2.0",
+    open_weights=True,
+    public_training_code="https://github.com/google-research/big_vision/blob/main/big_vision/trainers/proj/image_text/siglip.py",
     public_training_data=None,
     framework=["PyTorch"],
-    reference=None,
+    reference="https://huggingface.co/google/siglip-base-patch16-512",
     similarity_fn_name=None,
-    use_instructions=None,
-    training_datasets=None,
+    use_instructions=False,
+    training_datasets=siglip_training_datasets,
 )
 
 siglip_base_patch16_384 = ModelMeta(
@@ -309,18 +313,18 @@ def get_fused_embeddings(
     revision="41aec1c83b32e0a6fca20ad88ba058aa5b5ea394",
     release_date="2024-01-08",
     modalities=["image", "text"],
-    n_parameters=None,
-    max_tokens=None,
-    embed_dim=None,
-    license=None,
-    open_weights=None,
-    public_training_code=None,
+    n_parameters=203_000_000,
+    max_tokens=64,
+    embed_dim=768,
+    license="apache-2.0",
+    open_weights=True,
+    public_training_code="https://github.com/google-research/big_vision/blob/main/big_vision/trainers/proj/image_text/siglip.py",
     public_training_data=None,
     framework=["PyTorch"],
-    reference=None,
+    reference="https://huggingface.co/google/siglip-base-patch16-384",
     similarity_fn_name=None,
-    use_instructions=None,
-    training_datasets=None,
+    use_instructions=False,
+    training_datasets=siglip_training_datasets,
 )
 
 siglip_base_patch16_224 = ModelMeta(
@@ -333,18 +337,18 @@ def get_fused_embeddings(
     revision="7fd15f0689c79d79e38b1c2e2e2370a7bf2761ed",
     release_date="2024-01-08",
     modalities=["image", "text"],
-    n_parameters=None,
-    max_tokens=None,
-    embed_dim=None,
-    license=None,
-    open_weights=None,
-    public_training_code=None,
+    n_parameters=203_000_000,
+    max_tokens=64,
+    embed_dim=768,
+    license="apache-2.0",
+    open_weights=True,
+    public_training_code="https://github.com/google-research/big_vision/blob/main/big_vision/trainers/proj/image_text/siglip.py",
     public_training_data=None,
     framework=["PyTorch"],
-    reference=None,
+    reference="https://huggingface.co/google/siglip-base-patch16-224",
     similarity_fn_name=None,
-    use_instructions=None,
-    training_datasets=None,
+    use_instructions=False,
+    training_datasets=siglip_training_datasets,
 )
 
 siglip_large_patch16_256 = ModelMeta(
@@ -357,18 +361,18 @@ def get_fused_embeddings(
     revision="d0da9f876e7d66b4e250cd2450c3ba2ce735e447",
     release_date="2024-01-08",
     modalities=["image", "text"],
-    n_parameters=None,
-    max_tokens=None,
-    embed_dim=None,
-    license=None,
-    open_weights=None,
-    public_training_code=None,
+    n_parameters=652_000_000,
+    max_tokens=64,
+    embed_dim=1024,
+    license="apache-2.0",
+    open_weights=True,
+    public_training_code="https://github.com/google-research/big_vision/blob/main/big_vision/trainers/proj/image_text/siglip.py",
     public_training_data=None,
     framework=["PyTorch"],
-    reference=None,
+    reference="https://huggingface.co/google/siglip-large-patch16-256",
     similarity_fn_name=None,
-    use_instructions=None,
-    training_datasets=None,
+    use_instructions=False,
+    training_datasets=siglip_training_datasets,
 )
 
 siglip_large_patch16_384 = ModelMeta(
@@ -381,18 +385,18 @@ def get_fused_embeddings(
     revision="ce005573a40965dfd21fd937fbdeeebf2439fc35",
     release_date="2024-01-08",
     modalities=["image", "text"],
-    n_parameters=None,
-    max_tokens=None,
-    embed_dim=None,
-    license=None,
-    open_weights=None,
-    public_training_code=None,
+    n_parameters=652_000_000,
+    max_tokens=64,
+    embed_dim=1024,
+    license="apache-2.0",
+    open_weights=True,
+    public_training_code="https://github.com/google-research/big_vision/blob/main/big_vision/trainers/proj/image_text/siglip.py",
     public_training_data=None,
     framework=["PyTorch"],
-    reference=None,
+    reference="https://huggingface.co/google/siglip-large-patch16-384",
     similarity_fn_name=None,
-    use_instructions=None,
-    training_datasets=None,
+    use_instructions=False,
+    training_datasets=siglip_training_datasets,
 )
 
 if __name__ == "__main__":