ijepa_vitg16_22k

.gitattributes

@@ -608,3 +608,4 @@ ViT-gopt-16-SigLIP2-384__webli/visual/rknpu/rk3576/model.rknn filter=lfs diff=lf
 ViT-gopt-16-SigLIP2-384__webli/visual/rknpu/rk3588/model.rknn filter=lfs diff=lfs merge=lfs -text
 ViT-gopt-16-SigLIP2-384__webli/visual/visual.trunk.patch_embed.proj.weight filter=lfs diff=lfs merge=lfs -text
 ViT-gopt-16-SigLIP2-384__webli/visual/visual.trunk.pos_embed filter=lfs diff=lfs merge=lfs -text
+ijepa_vitg16_22k/onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text

ijepa_vitg16_22k/.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text

ijepa_vitg16_22k/README.md

@@ -0,0 +1,38 @@
+---
+library_name: transformers.js
+base_model: jmtzt/ijepa_vitg16_22k
+---
+
+https://huggingface.co/jmtzt/ijepa_vitg16_22k with ONNX weights to be compatible with Transformers.js.
+## Usage (Transformers.js)
+
+If you haven't already, you can install the [Transformers.js](https://huggingface.co/docs/transformers.js) JavaScript library from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
+```bash
+npm i @huggingface/transformers
+```
+
+**Example:** Image feature extraction with `onnx-community/ijepa_vitg16_22k`.
+
+```js
+import { pipeline, cos_sim } from "@huggingface/transformers";
+
+// Create an image feature extraction pipeline
+const extractor = await pipeline(
+  "image-feature-extraction",
+  "onnx-community/ijepa_vitg16_22k",
+  { dtype: "q8" },
+);
+
+// Compute image embeddings
+const url_1 = "http://images.cocodataset.org/val2017/000000039769.jpg"
+const url_2 = "http://images.cocodataset.org/val2017/000000219578.jpg"
+const output = await extractor([url_1, url_2]);
+const pooled_output = output.mean(1); // Apply mean pooling
+
+// Compute cosine similarity
+const similarity = cos_sim(pooled_output[0].data, pooled_output[1].data);
+console.log(similarity); // 0.4707813467804588
+```
+
+---
+Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).

ijepa_vitg16_22k/config.json

@@ -0,0 +1,28 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "jmtzt/ijepa_vitg16_22k",
+  "architectures": [
+    "IJepaModel"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1408,
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "layer_norm_eps": 1e-06,
+  "mlp_ratio": 4.363636363636363,
+  "model_type": "ijepa",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 40,
+  "patch_size": 16,
+  "qkv_bias": true,
+  "transformers_version": "4.47.0.dev0",
+  "transformers.js_config": {
+    "use_external_data_format": {
+      "model.onnx": true
+    }
+  }
+}

ijepa_vitg16_22k/onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd317571b0c27120b9245ab8ace6bafa1aa9305a40fc41224f9913ea1496898
+size 747004

ijepa_vitg16_22k/onnx/model.onnx_data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a527f6aab0e62533fcd45b63d28c3020cafa6d746b4cf22e94e5d6105d9661f
+size 4045474304

ijepa_vitg16_22k/onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d6a0173abb641e03291d179d116d2806d4d6af69fb941ce8ba3772ce3b8b33
+size 576906286

ijepa_vitg16_22k/onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd541c7e4fd4339d0e5252037cefb7a45f2d0bb2dba0f8cc91d4230f982172d4
+size 2023444063

ijepa_vitg16_22k/onnx/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:783defb8139f767064d09c507e954ca2ed49252388475d4fbe3cb3da3b056c21
+size 1018108033

ijepa_vitg16_22k/onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e2cda511ff00bafce4aefcdfd7f18b7f27a195ed196c4574082ed79b96cc7c
+size 639982726

ijepa_vitg16_22k/onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b6ae3e028b7e5c481d27f57a6ec87640bf59eb3685cc5c6a556d5b3be30e02
+size 572676122

ijepa_vitg16_22k/onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc647a73dd779ece8def37e3e119d248ab1e39a41f4be64fd119f3e00b7af04
+size 1018108033

ijepa_vitg16_22k/onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc647a73dd779ece8def37e3e119d248ab1e39a41f4be64fd119f3e00b7af04
+size 1018108033

ijepa_vitg16_22k/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

ijepa_vitg16_22k/quantize_config.json

@@ -0,0 +1,18 @@
+{
+    "modes": [
+        "fp16",
+        "q8",
+        "int8",
+        "uint8",
+        "q4",
+        "q4f16",
+        "bnb4"
+    ],
+    "per_channel": true,
+    "reduce_range": true,
+    "block_size": null,
+    "is_symmetric": true,
+    "accuracy_level": null,
+    "quant_type": 1,
+    "op_block_list": null
+}

ijepa_vitg16_22k/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/onnx-community/ijepa_vitg16_22k