Fix AutoModel loading, add image processor and Apache-2.0 license

LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,4 +1,5 @@
 ---
+license: apache-2.0
 library_name: transformers
 tags:
 - siglip
@@ -9,7 +10,7 @@ tags:
 - multimodal
 - image-text-embeddings
 - pet-recognition
-model_id: AvitoTech/SigLIP2-giant-e5small-v2-gating-for-animal-identification
+model_id: AvitoTech/SigLIP2-giant-e5small-v2-gating
 pipeline_tag: feature-extraction
 ---
 
@@ -109,87 +110,32 @@ The model has been benchmarked against various vision encoders on multiple pet r
 ### Installation
 
 ```bash
-pip install transformers torch pillow safetensors huggingface_hub
+pip install transformers torch pillow
 ```
 
 ### Load Model and Get Embedding
 
 ```python
 import torch
-import torch.nn as nn
-import torch.nn.functional as F
 from PIL import Image
-from transformers import SiglipModel, SiglipProcessor, AutoModel, AutoTokenizer
-from safetensors.torch import load_file
-from huggingface_hub import hf_hub_download
-
-# Define the model architecture
-class FaceRecognizer(nn.Module):
-    def __init__(self, embedding_dim=512):
-        super().__init__()
-        ckpt = "google/siglip2-giant-opt-patch16-384"
-        self.clip = SiglipModel.from_pretrained(ckpt)
-        self.processor = SiglipProcessor.from_pretrained(ckpt)
-        
-        text_model_name = "intfloat/e5-small-v2"
-        self.text_encoder = AutoModel.from_pretrained(text_model_name)
-        self.tokenizer = AutoTokenizer.from_pretrained(text_model_name)
-        
-        img_dim = self.clip.config.vision_config.hidden_size
-        text_dim = self.text_encoder.config.hidden_size
-        
-        self.proj_img = nn.Linear(img_dim, embedding_dim)
-        self.proj_text = nn.Linear(text_dim, embedding_dim)
-        
-        self.gate = nn.Sequential(
-            nn.Linear(embedding_dim * 2, 128),
-            nn.ReLU(),
-            nn.Linear(128, 2),
-            nn.Softmax(dim=-1)
-        )
-    
-    def average_pool(self, last_hidden_states, attention_mask):
-        last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
-        return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
-    
-    def forward(self, images, texts):
-        device = next(self.parameters()).device
-        
-        clip_inputs = self.processor(images=images, return_tensors="pt").to(device)
-        img_emb = self.clip.get_image_features(**clip_inputs)
-        
-        text_inputs = self.tokenizer(
-            texts, padding=True, truncation=True, max_length=512, return_tensors="pt"
-        ).to(device)
-        text_outputs = self.text_encoder(**text_inputs)
-        text_emb = self.average_pool(text_outputs.last_hidden_state, text_inputs['attention_mask'])
-        
-        img_proj = self.proj_img(img_emb)
-        text_proj = self.proj_text(text_emb)
-        
-        fused = torch.cat([text_proj, img_proj], dim=-1)
-        w = self.gate(fused)
-        fused_emb = w[:, 0:1] * text_proj + w[:, 1:2] * img_proj
-        
-        return F.normalize(fused_emb, dim=1)
-
-# Load model
-model = FaceRecognizer()
-
-# Download and load weights from HuggingFace
-weights_path = hf_hub_download(repo_id="AvitoTech/SigLIP2-giant-e5small-v2-gating-for-animal-identification", filename="model.safetensors")
-state_dict = load_file(weights_path)
-model.load_state_dict(state_dict)
+from transformers import AutoImageProcessor, AutoModel, AutoTokenizer
+
+repo = "AvitoTech/SigLIP2-giant-e5small-v2-gating"
+model = AutoModel.from_pretrained(repo, trust_remote_code=True).eval()
+image_processor = AutoImageProcessor.from_pretrained(repo)
+tokenizer = AutoTokenizer.from_pretrained(repo)
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
-model = model.to(device).eval()
+model = model.to(device)
 
-# Get fused embedding
 image = Image.open("your_image.jpg").convert("RGB")
 text = "orange cat"
 
 with torch.no_grad():
-    embedding = model([image], [text])
+    inputs = image_processor(images=[image], return_tensors="pt")
+    inputs.update(tokenizer([text], padding=True, truncation=True,
+                            max_length=512, return_tensors="pt"))
+    embedding = model(**inputs.to(device)).embeds
 
 print(f"Embedding shape: {embedding.shape}")  # torch.Size([1, 512])
 ```

config.json

@@ -1,48 +1,62 @@
-{
-  "architectures": [
-    "SiglipModel"
-  ],
-  "model_type": "siglip",
-  "text_config": {
-    "architectures": [
-      "SiglipTextModel"
-    ],
-    "attention_dropout": 0.0,
-    "dropout": 0.0,
-    "hidden_act": "gelu",
-    "hidden_size": 1152,
-    "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 4608,
-    "layer_norm_eps": 1e-06,
-    "max_position_embeddings": 64,
-    "model_type": "siglip_text_model",
-    "num_attention_heads": 16,
-    "num_hidden_layers": 32,
-    "pad_token_id": 0,
-    "vocab_size": 32000
-  },
-  "vision_config": {
-    "architectures": [
-      "SiglipVisionModel"
-    ],
-    "attention_dropout": 0.0,
-    "dropout": 0.0,
-    "hidden_act": "gelu",
-    "hidden_size": 1152,
-    "image_size": 384,
-    "initializer_factor": 1.0,
-    "initializer_range": 0.02,
-    "intermediate_size": 4608,
-    "layer_norm_eps": 1e-06,
-    "model_type": "siglip_vision_model",
-    "num_attention_heads": 16,
-    "num_channels": 3,
-    "num_hidden_layers": 32,
-    "patch_size": 16
-  },
-  "vision_dim": 1152,
-  "text_dim": 384,
-  "embedding_dim": 512,
-  "note": "Includes text encoder projections and gating mechanism"
-}
+{
+  "model_type": "avito_gated_fusion",
+  "architectures": [
+    "AvitoGatedFusionModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_avito_gated.AvitoGatedFusionConfig",
+    "AutoModel": "modeling_avito_gated.AvitoGatedFusionModel"
+  },
+  "embedding_dim": 512,
+  "gate_hidden_dim": 128,
+  "siglip_config": {
+    "initializer_factor": 1.0,
+    "model_type": "siglip",
+    "text_config": {
+      "vocab_size": 256000,
+      "hidden_size": 1152,
+      "intermediate_size": 4304,
+      "num_hidden_layers": 27,
+      "num_attention_heads": 16,
+      "max_position_embeddings": 64,
+      "layer_norm_eps": 1e-06,
+      "hidden_act": "gelu_pytorch_tanh",
+      "attention_dropout": 0.0,
+      "projection_size": 1536,
+      "model_type": "siglip_text_model"
+    },
+    "vision_config": {
+      "hidden_size": 1536,
+      "intermediate_size": 6144,
+      "num_hidden_layers": 40,
+      "num_attention_heads": 16,
+      "num_channels": 3,
+      "patch_size": 16,
+      "image_size": 384,
+      "attention_dropout": 0.0,
+      "layer_norm_eps": 1e-06,
+      "hidden_act": "gelu_pytorch_tanh",
+      "model_type": "siglip_vision_model"
+    }
+  },
+  "text_config": {
+    "pad_token_id": 0,
+    "model_type": "bert",
+    "vocab_size": 30522,
+    "hidden_size": 384,
+    "num_hidden_layers": 12,
+    "num_attention_heads": 12,
+    "hidden_act": "gelu",
+    "intermediate_size": 1536,
+    "hidden_dropout_prob": 0.1,
+    "attention_probs_dropout_prob": 0.1,
+    "max_position_embeddings": 512,
+    "type_vocab_size": 2,
+    "initializer_range": 0.02,
+    "layer_norm_eps": 1e-12,
+    "position_embedding_type": "absolute",
+    "use_cache": true,
+    "classifier_dropout": null
+  },
+  "dtype": "float32"
+}

configuration_avito_gated.py

@@ -0,0 +1,51 @@
+"""Configuration for the SigLIP2-Giant + E5-Small-v2 gated-fusion model."""
+
+from transformers import BertConfig, SiglipConfig
+from transformers.configuration_utils import PretrainedConfig
+
+
+class AvitoGatedFusionConfig(PretrainedConfig):
+    """Config for `AvitoGatedFusionModel`.
+
+    The model is a composite: a SigLIP2 tower (`siglip_config`) supplies the image
+    embedding, a BERT-style tower (`text_config`) supplies the text embedding, both
+    are projected to `embedding_dim` and mixed by a learned 2-way gate.
+    """
+
+    model_type = "avito_gated_fusion"
+    sub_configs = {"siglip_config": SiglipConfig, "text_config": BertConfig}
+
+    def __init__(
+        self,
+        siglip_config=None,
+        text_config=None,
+        embedding_dim=512,
+        gate_hidden_dim=128,
+        **kwargs,
+    ):
+        if siglip_config is None:
+            siglip_config = {}
+        if text_config is None:
+            text_config = {}
+        if isinstance(siglip_config, dict):
+            siglip_config = SiglipConfig(**siglip_config)
+        if isinstance(text_config, dict):
+            text_config = BertConfig(**text_config)
+
+        self.siglip_config = siglip_config
+        self.text_config = text_config
+        self.embedding_dim = embedding_dim
+        self.gate_hidden_dim = gate_hidden_dim
+
+        super().__init__(**kwargs)
+
+    @property
+    def image_embed_dim(self):
+        return self.siglip_config.vision_config.hidden_size
+
+    @property
+    def text_embed_dim(self):
+        return self.text_config.hidden_size
+
+
+__all__ = ["AvitoGatedFusionConfig"]

modeling_avito_gated.py

@@ -0,0 +1,129 @@
+"""SigLIP2-Giant + E5-Small-v2 gated-fusion model for animal identification.
+
+This mirrors, one-for-one, the `FaceRecognizer` wrapper the checkpoint was trained
+with (see the model card): the tensor names in `model.safetensors` are exactly the
+attribute names used here, so the published weights load unchanged.
+"""
+
+from dataclasses import dataclass
+from typing import Optional
+
+import torch
+import torch.nn.functional as F
+from torch import nn
+from transformers import BertModel, SiglipModel
+from transformers.modeling_outputs import ModelOutput
+from transformers.modeling_utils import PreTrainedModel
+
+from .configuration_avito_gated import AvitoGatedFusionConfig
+
+
+@dataclass
+class AvitoGatedFusionOutput(ModelOutput):
+    """
+    Args:
+        embeds: L2-normalised fused embedding, `(batch, embedding_dim)`.
+        image_embeds: image embedding after `proj_img`, `(batch, embedding_dim)`.
+        text_embeds: text embedding after `proj_text`, `(batch, embedding_dim)`.
+        gate_weights: gate output, `(batch, 2)`, ordered `[text, image]`.
+    """
+
+    embeds: Optional[torch.FloatTensor] = None
+    image_embeds: Optional[torch.FloatTensor] = None
+    text_embeds: Optional[torch.FloatTensor] = None
+    gate_weights: Optional[torch.FloatTensor] = None
+
+
+class AvitoGatedFusionModel(PreTrainedModel):
+    config_class = AvitoGatedFusionConfig
+    # Deliberately not a prefix that appears in the checkpoint, so that the
+    # `clip.` / `text_encoder.` keys are loaded verbatim.
+    base_model_prefix = "avito_gated_fusion"
+    main_input_name = "pixel_values"
+    _supports_sdpa = True
+    supports_gradient_checkpointing = True
+
+    def __init__(self, config: AvitoGatedFusionConfig):
+        super().__init__(config)
+        self.clip = SiglipModel(config.siglip_config)
+        self.text_encoder = BertModel(config.text_config)
+        self.proj_img = nn.Linear(config.image_embed_dim, config.embedding_dim)
+        self.proj_text = nn.Linear(config.text_embed_dim, config.embedding_dim)
+        self.gate = nn.Sequential(
+            nn.Linear(config.embedding_dim * 2, config.gate_hidden_dim),
+            nn.ReLU(),
+            nn.Linear(config.gate_hidden_dim, 2),
+            nn.Softmax(dim=-1),
+        )
+        self.post_init()
+
+    def _init_weights(self, module):
+        std = getattr(self.config, "initializer_range", 0.02)
+        if isinstance(module, (nn.Linear, nn.Conv2d)):
+            module.weight.data.normal_(mean=0.0, std=std)
+            if module.bias is not None:
+                module.bias.data.zero_()
+        elif isinstance(module, nn.Embedding):
+            module.weight.data.normal_(mean=0.0, std=std)
+            if module.padding_idx is not None:
+                module.weight.data[module.padding_idx].zero_()
+        elif isinstance(module, nn.LayerNorm):
+            module.bias.data.zero_()
+            module.weight.data.fill_(1.0)
+        elif isinstance(module, nn.Parameter):
+            module.data.normal_(mean=0.0, std=std)
+
+    @staticmethod
+    def average_pool(last_hidden_states: torch.Tensor, attention_mask: torch.Tensor) -> torch.Tensor:
+        last_hidden = last_hidden_states.masked_fill(~attention_mask[..., None].bool(), 0.0)
+        return last_hidden.sum(dim=1) / attention_mask.sum(dim=1)[..., None]
+
+    def get_image_features(self, pixel_values: torch.FloatTensor, **kwargs) -> torch.FloatTensor:
+        """Raw SigLIP2 image embedding, `(batch, image_embed_dim)`."""
+        return self.clip.get_image_features(pixel_values=pixel_values, **kwargs)
+
+    def get_text_features(
+        self,
+        input_ids: torch.LongTensor,
+        attention_mask: torch.Tensor,
+        token_type_ids: Optional[torch.Tensor] = None,
+        **kwargs,
+    ) -> torch.FloatTensor:
+        """Mean-pooled E5 text embedding, `(batch, text_embed_dim)`."""
+        outputs = self.text_encoder(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            token_type_ids=token_type_ids,
+            **kwargs,
+        )
+        return self.average_pool(outputs.last_hidden_state, attention_mask)
+
+    def forward(
+        self,
+        pixel_values: torch.FloatTensor,
+        input_ids: torch.LongTensor,
+        attention_mask: torch.Tensor,
+        token_type_ids: Optional[torch.Tensor] = None,
+        return_dict: Optional[bool] = None,
+    ):
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        img_emb = self.get_image_features(pixel_values)
+        text_emb = self.get_text_features(input_ids, attention_mask, token_type_ids)
+
+        img_proj = self.proj_img(img_emb)
+        text_proj = self.proj_text(text_emb)
+
+        fused = torch.cat([text_proj, img_proj], dim=-1)
+        w = self.gate(fused)
+        fused_emb = w[:, 0:1] * text_proj + w[:, 1:2] * img_proj
+        embeds = F.normalize(fused_emb, dim=1)
+
+        if not return_dict:
+            return (embeds, img_proj, text_proj, w)
+        return AvitoGatedFusionOutput(
+            embeds=embeds, image_embeds=img_proj, text_embeds=text_proj, gate_weights=w
+        )
+
+
+__all__ = ["AvitoGatedFusionModel", "AvitoGatedFusionOutput"]

preprocessor_config.json

@@ -0,0 +1,24 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "SiglipProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 384,
+    "width": 384
+  }
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}