Add model

README.md

@@ -0,0 +1,22 @@
+---
+tags:
+- timm
+- transformers
+- image-feature-extraction
+- siglip
+- siglip2
+library_name: timm
+license: apache-2.0
+datasets:
+- webli
+---
+# Model card for vit_base_patch16_siglip_224.v2_webli
+
+A SigLIP 2 ViT (image encoder only) for `timm`. Equivalent to image tower from https://huggingface.co/timm/ViT-B-16-SigLIP2.
+
+
+## Model Details
+- **Dataset:** webli
+- **Papers:**
+  - SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features: https://arxiv.org/abs/2502.14786
+  - Sigmoid Loss for Language Image Pre-Training: https://arxiv.org/abs/2303.15343

config.json

@@ -0,0 +1,33 @@
+{
+  "architecture": "vit_base_patch16_siglip_224",
+  "num_classes": 0,
+  "num_features": 768,
+  "global_pool": "map",
+  "pretrained_cfg": {
+    "tag": "v2_webli",
+    "custom_load": false,
+    "input_size": [
+      3,
+      224,
+      224
+    ],
+    "fixed_input_size": true,
+    "interpolation": "bicubic",
+    "crop_pct": 0.9,
+    "crop_mode": "center",
+    "mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "num_classes": 0,
+    "pool_size": null,
+    "first_conv": "patch_embed.proj",
+    "classifier": "head"
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9106b0d8d9d02ea90fc3571fffd1557cf444736f695ee40b1e57c856bc3d9494
+size 371551936

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5df7fa97ed317f26362d9499f38b971e117751362a3f6ee1b7f92552d7faf23
+size 371597458