Upload folder using huggingface_hub

README.md

@@ -1,3 +1,68 @@
----
-license: cc-by-nc-4.0
----
+---
+library_name: transformers
+pipeline_tag: zero-shot-image-classification
+license: cc-by-nc-4.0
+tags:
+- clip
+- multilingual
+---
+
+# Model Card for Distilled MetaCLIP 2 ViT-S/16 (mT5 Tokenizer) (worldwide)
+
+Distilled MetaCLIP 2 (worldwide) was presented in [MetaCLIP 2: A Worldwide Scaling Recipe](https://huggingface.co/papers/2507.22062).
+
+This checkpoint corresponds to "ViT-S-16-mT5-worldwide" of the [original implementation](https://github.com/facebookresearch/MetaCLIP).
+
+## Install
+
+First install the Transformers library (from source for now):
+
+```bash
+pip install -q git+https://github.com/huggingface/transformers.git
+```
+
+## Usage
+
+Next you can use it like so:
+
+```python
+import torch
+from transformers import pipeline
+
+clip = pipeline(
+   task="zero-shot-image-classification",
+   model="facebook/metaclip-2-mt5-worldwide-s16",
+   torch_dtype=torch.bfloat16,
+   device=0
+)
+labels = ["a photo of a cat", "a photo of a dog", "a photo of a car"]
+
+results = clip("http://images.cocodataset.org/val2017/000000039769.jpg", candidate_labels=labels)
+print(results)
+```
+
+In case you want to perform pre- and postprocessing yourself, you can use the `AutoModel` API:
+
+```python
+import requests
+import torch
+from PIL import Image
+from transformers import AutoProcessor, AutoModel
+
+# note: make sure to verify that `AutoModel` is an instance of `MetaClip2Model`
+model = AutoModel.from_pretrained("facebook/metaclip-2-mt5-worldwide-s16", torch_dtype=torch.bfloat16, attn_implementation="sdpa")
+processor = AutoProcessor.from_pretrained("facebook/metaclip-2-mt5-worldwide-s16")
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+labels = ["a photo of a cat", "a photo of a dog", "a photo of a car"]
+
+inputs = processor(text=labels, images=image, return_tensors="pt", padding=True)
+
+outputs = model(**inputs)
+logits_per_image = outputs.logits_per_image
+probs = logits_per_image.softmax(dim=1)
+most_likely_idx = probs.argmax(dim=1).item()
+most_likely_label = labels[most_likely_idx]
+print(f"Most likely label: {most_likely_label} with probability: {probs[0][most_likely_idx].item():.3f}")
+```

config.json

@@ -0,0 +1,43 @@
+{
+  "architectures": [
+    "MetaClip2Model"
+  ],
+  "dtype": "float32",
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "metaclip_2",
+  "projection_dim": 384,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "eos_token_id": 1,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "metaclip_2_text_model",
+    "num_attention_heads": 6,
+    "num_hidden_layers": 12,
+    "projection_dim": 384,
+    "vocab_size": 250000
+  },
+  "transformers_version": "4.57.1",
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 384,
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 1536,
+    "layer_norm_eps": 1e-05,
+    "model_type": "metaclip_2_vision_model",
+    "num_attention_heads": 6,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 384
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c3d2c36fddc03e0fd5576d09195f97d85d293acfc985600b5088fc9fd83101d
+size 557186884

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "CLIPProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "added_tokens_decoder": {
+    "1": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids"
+  ],
+  "model_max_length": 64,
+  "pad_token": "</s>",
+  "processor_class": "CLIPProcessor",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "SiglipTokenizer",
+  "unk_token": "<unk>"
+}