Upload folder using huggingface_hub

README.md

@@ -0,0 +1,81 @@
+---
+pipeline_tag: image-classification
+license: apache-2.0
+base_model: microsoft/beit-large-patch16-512
+library_name: zeromodels
+tags:
+- keras
+- zeromodels
+- beit
+- image-classification
+- vit
+- backbone
+- arxiv:2106.08254
+- pytorch
+- jax
+- tf
+---
+
+## ***See [our collection](https://huggingface.co/collections/zeromodels/beit-6a9352067192fd9fcfcfe6f1) for all versions of BEiT.***
+
+# Run BEiT with Keras 3: JAX, PyTorch, or TensorFlow
+
+[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-black?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-BEiT-blue)](https://imvision12.github.io/ZeroModels/beit/) [![Collection](https://img.shields.io/badge/HF-BEiT%20collection-yellow)](https://huggingface.co/collections/zeromodels/beit-6a9352067192fd9fcfcfe6f1)
+
+# zeromodels/beit-large-patch16-512
+
+Paper: [BEiT: BERT Pre-Training of Image Transformers (arXiv:2106.08254)](https://arxiv.org/abs/2106.08254) · [HF Papers](https://huggingface.co/papers/2106.08254)
+
+BEiT is a ViT-family vision transformer with a per-layer relative position bias, a learnable layer scale on each residual branch, and mean pooling of the patch tokens. Large backbone fine-tuned on ImageNet-1k at 512x512 (1000 classes).
+
+For more details on the model, please go to Microsoft's original [model card](https://huggingface.co/microsoft/beit-large-patch16-512).
+
+Pure-**Keras 3** conversion of [`microsoft/beit-large-patch16-512`](https://huggingface.co/microsoft/beit-large-patch16-512) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
+
+This is a **image classification** checkpoint (`BeitImageClassify`).
+
+## ✨ Quick start
+
+```python
+import os
+os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
+
+import keras
+import numpy as np
+from PIL import Image
+from zeromodels.models.beit import BeitImageClassify
+
+model = BeitImageClassify.from_weights("zeromodels/beit-large-patch16-512")
+
+image = Image.open("your_image.jpg").convert("RGB").resize((512, 512))
+pixels = np.asarray(image, "float32")[None]  # raw [0, 255]; normalization is inside the model
+logits = model(pixels, training=False)
+print("top-1 class id:", int(keras.ops.convert_to_numpy(logits)[0].argmax()))
+```
+
+Load any BEiT variant the same way with `from_weights("zeromodels/<variant>")`:
+
+| Variant | Hub | Task |
+|---|---|---|
+| `beit-base-patch16-224` | [`zeromodels/beit-base-patch16-224`](https://huggingface.co/zeromodels/beit-base-patch16-224) | image classification |
+| `beit-large-patch16-224` | [`zeromodels/beit-large-patch16-224`](https://huggingface.co/zeromodels/beit-large-patch16-224) | image classification |
+| `beit-large-patch16-512` | [`zeromodels/beit-large-patch16-512`](https://huggingface.co/zeromodels/beit-large-patch16-512) | image classification |
+| `beit-base-patch16-224-pt22k-ft22k` | [`zeromodels/beit-base-patch16-224-pt22k-ft22k`](https://huggingface.co/zeromodels/beit-base-patch16-224-pt22k-ft22k) | image classification |
+| `beit-large-patch16-224-pt22k-ft22k` | [`zeromodels/beit-large-patch16-224-pt22k-ft22k`](https://huggingface.co/zeromodels/beit-large-patch16-224-pt22k-ft22k) | image classification |
+| `beit-base-finetuned-ade-640-640` | [`zeromodels/beit-base-finetuned-ade-640-640`](https://huggingface.co/zeromodels/beit-base-finetuned-ade-640-640) | semantic segmentation |
+| `beit-large-finetuned-ade-640-640` | [`zeromodels/beit-large-finetuned-ade-640-640`](https://huggingface.co/zeromodels/beit-large-finetuned-ade-640-640) | semantic segmentation |
+
+## Tips
+
+- Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
+- Normalization (0.5/0.5) is baked into the model, so pass raw `[0, 255]` pixels.
+- Classification uses `BeitImageClassify`; semantic segmentation uses `BeitSemanticSegment` and returns logits at a quarter of the input resolution (upsample the `argmax` map to the input size).
+- `BeitModel.from_weights(..., as_backbone=True)` returns the per-block token sequences for feature extraction.
+- See [BEiT docs](https://imvision12.github.io/ZeroModels/beit/) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/).
+- Community / upstream safetensors still work via the `hf:` prefix, e.g. `BeitImageClassify.from_weights("hf:microsoft/beit-large-patch16-512")`.
+
+## Special Thanks
+
+A huge thank you to the Microsoft Research BEiT authors for creating and releasing these models.
+
+License: Apache 2.0.

model.weights.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fccf87cb9bbca625552b0bb3459e5a6e8b2b99207a4a4c91784a23fa58cf436
+size 1223582304

zm_config.json

@@ -0,0 +1,34 @@
+{
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.2.7",
+  "model_module": "zeromodels.models.beit",
+  "model_class": "BeitImageClassify",
+  "variant": "beit-large-patch16-512",
+  "weights": "model.weights.h5",
+  "schema_version": 2,
+  "model_type": "beit",
+  "vision_config": {
+    "hidden_size": 1024,
+    "num_hidden_layers": 24,
+    "num_attention_heads": 16,
+    "intermediate_size": 4096,
+    "image_size": 512,
+    "patch_size": 16,
+    "num_channels": 3,
+    "layer_scale_init_value": 0.1,
+    "layer_norm_eps": 1e-12,
+    "num_classes": 1000,
+    "out_indices": [
+      3,
+      5,
+      7,
+      11
+    ],
+    "pool_scales": [
+      1,
+      2,
+      3,
+      6
+    ]
+  }
+}