fix: sentence-transformers support

README.md

@@ -0,0 +1,164 @@
+---
+tags:
+- clip
+- transformers
+- e-commerce
+- fashion
+- multimodal retrieval
+- siglip
+- transformers.js
+library_name: open_clip
+pipeline_tag: zero-shot-image-classification
+license: apache-2.0
+language:
+- en
+metrics:
+- precision
+- recall
+- MRR
+---
+# Marqo-FashionSigLIP Model Card
+
+[![GitHub](https://img.shields.io/badge/GitHub-black?logo=github)](https://github.com/marqo-ai/marqo-FashionCLIP)
+
+Marqo-FashionSigLIP is a multimodal embedding model that provides up to [57% improvement in MRR and recall](https://www.marqo.ai/blog/search-model-for-fashion) over [fashion clip](https://huggingface.co/patrickjohncyh/fashion-clip). 
+
+Marqo-FashionSigLIP leverages Generalised Contrastive Learning ([GCL](https://www.marqo.ai/blog/generalized-contrastive-learning-for-multi-modal-retrieval-and-ranking)) which allows the model to be trained on not just text descriptions but also categories, style, colors, materials, keywords and fine-details to provide highly relevant search results on fashion products. 
+The model was fine-tuned from ViT-B-16-SigLIP (webli). 
+
+**Github Page**: [Marqo-FashionCLIP](https://github.com/marqo-ai/marqo-FashionCLIP)
+
+**Blog**: [Marqo Blog](https://www.marqo.ai/blog/search-model-for-fashion)
+
+
+## Usage
+
+### Hugging Face
+
+The model can be loaded with AutoModel by
+
+```python
+from transformers import AutoModel, AutoProcessor
+model = AutoModel.from_pretrained('Marqo/marqo-fashionSigLIP', trust_remote_code=True)
+processor = AutoProcessor.from_pretrained('Marqo/marqo-fashionSigLIP', trust_remote_code=True)
+
+import torch
+from PIL import Image
+
+image = [Image.open("docs/fashion-hippo.png")]
+text = ["a hat", "a t-shirt", "shoes"]
+processed = processor(text=text, images=image, padding='max_length', return_tensors="pt")
+
+with torch.no_grad():
+    image_features = model.get_image_features(processed['pixel_values'], normalize=True)
+    text_features = model.get_text_features(processed['input_ids'], normalize=True)
+
+    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)
+
+print("Label probs:", text_probs)
+# [0.98379946, 0.01294010, 0.00326044]
+```
+
+### OpenCLIP
+
+The model can be seamlessly used with [OpenCLIP](https://github.com/mlfoundations/open_clip) by
+
+```python
+import open_clip
+model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:Marqo/marqo-fashionSigLIP')
+tokenizer = open_clip.get_tokenizer('hf-hub:Marqo/marqo-fashionSigLIP')
+
+import torch
+from PIL import Image
+
+image = preprocess_val(Image.open("docs/fashion-hippo.png")).unsqueeze(0)
+text = tokenizer(["a hat", "a t-shirt", "shoes"])
+
+with torch.no_grad(), torch.cuda.amp.autocast():
+    image_features = model.encode_image(image, normalize=True)
+    text_features = model.encode_text(text, normalize=True)
+
+    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)
+
+print("Label probs:", text_probs)
+# [0.9860219105287394, 0.00777916527489097, 0.006198924196369721]
+```
+
+### Transformers.js
+
+You can also run the model in JavaScript with the [Transformers.js](https://huggingface.co/docs/transformers.js) library.
+
+First, install it from [NPM](https://www.npmjs.com/package/@huggingface/transformers) using:
+
+```bash
+npm i @huggingface/transformers
+```
+
+Then, compute embeddings as follows:
+```js
+import { SiglipTextModel, SiglipVisionModel, AutoTokenizer, AutoProcessor, RawImage, softmax, dot } from '@huggingface/transformers';
+
+const model_id = 'Marqo/marqo-fashionSigLIP';
+
+// Load tokenizer and text model
+const tokenizer = await AutoTokenizer.from_pretrained(model_id);
+const text_model = await SiglipTextModel.from_pretrained(model_id);
+
+// Load processor and vision model
+const processor = await AutoProcessor.from_pretrained(model_id);
+const vision_model = await SiglipVisionModel.from_pretrained(model_id);
+
+// Run tokenization
+const texts = ['a hat', 'a t-shirt', 'shoes'];
+const text_inputs = tokenizer(texts, { padding: 'max_length', truncation: true });
+
+// Compute text embeddings
+const { text_embeds } = await text_model(text_inputs);
+
+// Read image and run processor
+const image = await RawImage.read('https://raw.githubusercontent.com/marqo-ai/marqo-FashionCLIP/main/docs/fashion-hippo.png');
+const image_inputs = await processor(image);
+
+// Compute vision embeddings
+const { image_embeds } = await vision_model(image_inputs);
+
+// Compute similarity scores
+const normalized_text_embeds = text_embeds.normalize().tolist();
+const normalized_image_embeds = image_embeds.normalize().tolist()[0];
+
+const text_probs = softmax(normalized_text_embeds.map((text_embed) => 
+    100.0 * dot(normalized_image_embeds, text_embed)
+));
+console.log(text_probs);
+// [0.9860219105287394, 0.00777916527489097, 0.006198924196369721]
+```
+
+## Benchmark Results
+Average evaluation results on 6 public multimodal fashion datasets ([Atlas](https://huggingface.co/datasets/Marqo/atlas), [DeepFashion (In-shop)](https://huggingface.co/datasets/Marqo/deepfashion-inshop), [DeepFashion (Multimodal)](https://huggingface.co/datasets/Marqo/deepfashion-multimodal), [Fashion200k](https://huggingface.co/datasets/Marqo/fashion200k), [KAGL](https://huggingface.co/datasets/Marqo/KAGL), and [Polyvore](https://huggingface.co/datasets/Marqo/polyvore)) are reported below: 
+
+**Text-To-Image (Averaged across 6 datasets)**
+| Model                      | AvgRecall   | Recall@1   | Recall@10   | MRR       |
+|----------------------------|-------------|------------|-------------|-----------|
+| Marqo-FashionSigLIP        | **0.231**   | **0.121**  | **0.340**   | **0.239** |
+| FashionCLIP2.0             | 0.163       | 0.077      | 0.249       | 0.165     |
+| OpenFashionCLIP            | 0.132       | 0.060      | 0.204       | 0.135     |
+| ViT-B-16-laion2b_s34b_b88k | 0.174       | 0.088      | 0.261       | 0.180     |
+| ViT-B-16-SigLIP-webli      | 0.212       | 0.111      | 0.314       | 0.214     |
+
+**Category-To-Product (Averaged across 5 datasets)**
+| Model                      | AvgP      | P@1       | P@10      | MRR       |
+|----------------------------|-----------|-----------|-----------|-----------|
+| Marqo-FashionSigLIP        | **0.737** | **0.758** | **0.716** | **0.812** |
+| FashionCLIP2.0             | 0.684     | 0.681     | 0.686     | 0.741     |
+| OpenFashionCLIP            | 0.646     | 0.653     | 0.639     | 0.720     |
+| ViT-B-16-laion2b_s34b_b88k | 0.662     | 0.673     | 0.652     | 0.743     |
+| ViT-B-16-SigLIP-webli      | 0.688     | 0.690     | 0.685     | 0.751     |
+
+**Sub-Category-To-Product (Averaged across 4 datasets)**
+| Model                      | AvgP      | P@1       | P@10      | MRR       |
+|----------------------------|-----------|-----------|-----------|-----------|
+| Marqo-FashionSigLIP        | **0.725** | **0.767** | **0.683** | **0.811** |
+| FashionCLIP2.0             | 0.657     | 0.676     | 0.638     | 0.733     |
+| OpenFashionCLIP            | 0.598     | 0.619     | 0.578     | 0.689     |
+| ViT-B-16-laion2b_s34b_b88k | 0.638     | 0.651     | 0.624     | 0.712     |
+| ViT-B-16-SigLIP-webli      | 0.643     | 0.643     | 0.643     | 0.726     |

config.json

@@ -0,0 +1,48 @@
+{
+  "auto_map": {
+    "AutoConfig": "marqo_fashionSigLIP.MarqoFashionSigLIPConfig",
+    "AutoModel": "marqo_fashionSigLIP.MarqoFashionSigLIP",
+    "AutoProcessor": "marqo_fashionSigLIP.MarqoFashionSigLIPProcessor"
+  },
+  "open_clip_model_name": "hf-hub:Marqo/marqo-fashionSigLIP",
+  "model_type": "siglip",
+  "hidden_size": 768,
+  "projection_dim": 768,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 49406,
+    "eos_token_id": 49407,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-6,
+    "max_position_embeddings": 64,
+    "model_type": "siglip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "pad_token_id": 1,
+    "transformers_version": "4.47.1",
+    "vocab_size": 32000
+  },
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "image_size": 224,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-6,
+    "model_type": "siglip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "transformers_version": "4.47.1"
+  },
+  "initializer_factor": 1.0,
+  "return_dict": true,
+  "output_hidden_states": false,
+  "output_attentions": false,
+  "torchscript": false,
+  "use_bfloat16": false,
+  "tie_word_embeddings": true
+}

marqo_fashionSigLIP.py

@@ -0,0 +1,237 @@
+import torch
+from open_clip import create_model
+from transformers import PretrainedConfig, PreTrainedModel
+from transformers.models.siglip.modeling_siglip import SiglipOutput
+from typing import Optional, Tuple, Union, List
+from transformers.feature_extraction_utils import BatchFeature
+from transformers.image_utils import ImageInput
+from transformers.processing_utils import ProcessorMixin
+from transformers.tokenization_utils_base import PaddingStrategy, PreTokenizedInput, TextInput, TruncationStrategy
+from transformers.utils import TensorType
+import string
+import ftfy
+import html
+
+def basic_clean(text):
+    text = ftfy.fix_text(text)
+    text = html.unescape(html.unescape(text))
+    return text.strip()
+
+def canonicalize_text(
+    text,
+    *,
+    keep_punctuation_exact_string=None,
+    trans_punctuation: dict = str.maketrans("", "", string.punctuation),
+):
+    """Returns canonicalized `text` (lowercase and punctuation removed).
+
+    From: https://github.com/google-research/big_vision/blob/53f18caf27a9419231bbf08d3388b07671616d3d/big_vision/evaluators/proj/image_text/prompt_engineering.py#L94
+
+    Args:
+      text: string to be canonicalized.
+      keep_punctuation_exact_string: If provided, then this exact string kept.
+        For example providing '{}' will keep any occurrences of '{}' (but will
+        still remove '{' and '}' that appear separately).
+    """
+    text = text.replace("_", " ")
+    if keep_punctuation_exact_string:
+        text = keep_punctuation_exact_string.join(
+            part.translate(trans_punctuation)
+            for part in text.split(keep_punctuation_exact_string)
+        )
+    else:
+        text = text.translate(trans_punctuation)
+    text = text.lower()
+    text = " ".join(text.split())
+    return text.strip()
+
+def _clean_canonicalize(x):
+    # basic, remove whitespace, remove punctuation, lower case
+    return canonicalize_text(basic_clean(x))
+
+class MarqoFashionSigLIPConfig(PretrainedConfig):
+    def __init__(
+        self,
+        open_clip_model_name: str = "",
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.open_clip_model_name = open_clip_model_name
+        
+class MarqoFashionSigLIPProcessor(ProcessorMixin):
+    r"""
+    Constructs a Siglip processor which wraps a Siglip image processor and a Siglip tokenizer into a single processor.
+
+    [`SiglipProcessor`] offers all the functionalities of [`SiglipImageProcessor`] and [`SiglipTokenizer`]. See the
+    [`~SiglipProcessor.__call__`] and [`~SiglipProcessor.decode`] for more information.
+
+    Args:
+        image_processor ([`SiglipImageProcessor`]):
+            The image processor is a required input.
+        tokenizer ([`T5TokenizerFast`]):
+            The tokenizer is a required input.
+    """
+
+    attributes = ["image_processor", "tokenizer"]
+    image_processor_class = "SiglipImageProcessor"
+    tokenizer_class = "T5TokenizerFast"
+
+    def __init__(self, image_processor, tokenizer):
+        super().__init__(image_processor, tokenizer)
+
+    def __call__(
+        self,
+        text: Union[TextInput, PreTokenizedInput, List[TextInput], List[PreTokenizedInput]] = None,
+        images: ImageInput = None,
+        padding: Union[bool, str, PaddingStrategy] = False,
+        truncation: Union[bool, str, TruncationStrategy] = None,
+        max_length: int = None,
+        return_tensors: Optional[Union[str, TensorType]] = TensorType.PYTORCH,
+    ) -> BatchFeature:
+        """
+        Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text`
+        and `kwargs` arguments to SiglipTokenizer's [`~SiglipTokenizer.__call__`] if `text` is not `None` to encode
+        the text. To prepare the image(s), this method forwards the `images` argument to
+        SiglipImageProcessor's [`~SiglipImageProcessor.__call__`] if `images` is not `None`. Please refer to the doctsring
+        of the above two methods for more information.
+
+        Args:
+            text (`str`, `List[str]`, `List[List[str]]`):
+                The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings
+                (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set
+                `is_split_into_words=True` (to lift the ambiguity with a batch of sequences).
+            images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`):
+                The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch
+                tensor. Both channels-first and channels-last formats are supported.
+            padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`):
+                Select a strategy to pad the returned sequences (according to the model's padding side and padding
+                index) among:
+                - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
+                  sequence if provided).
+                - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum
+                  acceptable input length for the model if that argument is not provided.
+                - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different
+                  lengths).
+            max_length (`int`, *optional*):
+                Maximum length of the returned list and optionally padding length (see above).
+            truncation (`bool`, *optional*):
+                Activates truncation to cut input sequences longer than `max_length` to `max_length`.
+            return_tensors (`str` or [`~utils.TensorType`], *optional*):
+                If set, will return tensors of a particular framework. Acceptable values are:
+
+                - `'tf'`: Return TensorFlow `tf.constant` objects.
+                - `'pt'`: Return PyTorch `torch.Tensor` objects.
+                - `'np'`: Return NumPy `np.ndarray` objects.
+                - `'jax'`: Return JAX `jnp.ndarray` objects.
+
+        Returns:
+            [`BatchFeature`]: A [`BatchFeature`] with the following fields:
+
+            - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
+            - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
+              `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
+              `None`).
+            - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`.
+        """
+
+        if text is None and images is None:
+            raise ValueError("You have to specify either text or images. Both cannot be none.")
+
+        if text is not None:
+            if isinstance(text, str):
+                text = [text]
+            text = [_clean_canonicalize(raw_text) for raw_text in text]
+            encoding = self.tokenizer(
+                text, return_tensors=return_tensors, padding=padding, truncation=truncation, max_length=max_length
+            )
+
+        if images is not None:
+            try:
+                images = [image.convert('RGB') for image in images] if isinstance(images, list) else images.convert('RGB')
+            except:
+                images = images
+            image_features = self.image_processor(images, return_tensors=return_tensors)
+
+        if text is not None and images is not None:
+            encoding["pixel_values"] = image_features.pixel_values
+            return encoding
+        elif text is not None:
+            return encoding
+        else:
+            return BatchFeature(data=dict(**image_features), tensor_type=return_tensors)
+
+    def decode(self, *args, **kwargs):
+        """
+        This method forwards all its arguments to SiglipTokenizer's [`~PreTrainedTokenizer.decode`]. Please refer to
+        the docstring of this method for more information.
+        """
+        return self.tokenizer.decode(*args, **kwargs)
+
+    def batch_decode(self, *args, **kwargs):
+        """
+        This method forwards all its arguments to SiglipTokenizer's [`~PreTrainedTokenizer.batch_decode`]. Please
+        refer to the docstring of this method for more information.
+        """
+        return self.tokenizer.batch_decode(*args, **kwargs)
+
+    @property
+    # Copied from transformers.models.clip.processing_clip.CLIPProcessor.model_input_names with CLIP->Siglip, T5->Siglip
+    def model_input_names(self):
+        tokenizer_input_names = self.tokenizer.model_input_names
+        image_processor_input_names = self.image_processor.model_input_names
+        return list(dict.fromkeys(tokenizer_input_names + image_processor_input_names))
+        
+class MarqoFashionSigLIP(PreTrainedModel):
+    config_class = MarqoFashionSigLIPConfig
+
+    def __init__(self, config: MarqoFashionSigLIPConfig):
+        super().__init__(config)
+        self.config = config
+        self.model = create_model(config.open_clip_model_name, output_dict=True)
+        self.model.eval()
+        self.model.to(self.device)
+        
+    def get_image_features(
+        self, 
+        pixel_values: torch.FloatTensor, 
+        normalize: bool = False,
+        **kwargs
+        ) -> torch.FloatTensor:
+        
+        with torch.inference_mode():
+            image_features = self.model.encode_image(pixel_values, normalize=normalize)
+        return image_features
+    
+    def get_text_features(
+        self,
+        input_ids: torch.Tensor,
+        normalize: bool = False,
+        **kwargs
+    ) -> torch.FloatTensor:
+        
+        with torch.inference_mode():
+            text_features = self.model.encode_text(input_ids, normalize=normalize)
+        return text_features
+        
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        pixel_values: Optional[torch.FloatTensor] = None,
+        return_dict: Optional[bool] = None,
+    ) -> Union[Tuple, SiglipOutput]:
+
+        vision_outputs = self.get_image_features(pixel_values=pixel_values, normalize=True)
+        text_outputs = self.get_text_features(input_ids=input_ids, normalize=True)
+
+        logits_per_text = text_outputs @ vision_outputs.T
+        logits_per_image = logits_per_text.T
+
+        if not return_dict:
+            return logits_per_image, logits_per_text, text_outputs, vision_outputs
+
+        return SiglipOutput(
+            logits_per_image=logits_per_image,
+            logits_per_text=logits_per_text,
+            text_embeds=text_outputs,
+            image_embeds=vision_outputs
+        )

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a58c671a74e072a677d565b515c23e14855f149db699db4be2ee81816019a07
+size 812660320

onnx/text_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d501b23bddf27ba828c037b0780e44fdf47ca4c0b925ef190ab5bcf7aaf6e6
+size 441361402

onnx/text_model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be58194517cdafe1695c2675259ffdba8871b77f8c5828cd45598177453f5d5
+size 173734396

onnx/text_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5fcccd805e8910663dcbd6821c3cbe040bbe508c656964de08736272228806
+size 220817780

onnx/text_model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a7995e029c6ee9346fa46857661c4a171d28b164fa7703b85a527d73adf170
+size 111125229

onnx/text_model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f62fd2b046d82ec1ed91881fe9f4f0b34d4e11bae539a33092712031ffee129
+size 178600156

onnx/text_model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48e36d0acdc1579aac8edb3c593a3f2ef9d55f7646b9e3acd7baf8f00d7d0ce
+size 108904023

onnx/text_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5a7995e029c6ee9346fa46857661c4a171d28b164fa7703b85a527d73adf170
+size 111125229

onnx/text_model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e45a29f61825b0fdc4ab2648c84791d6af1b63fe86ce7bd7c7fee43fc3b1c4d
+size 111125261

onnx/vision_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e773846b27a699c45ba7e3978514b7fca420662d7e69e3b9226982f09f4a13
+size 371715502

onnx/vision_model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7724073a1af61260bc4d250492ff1d2bfbf2e4d4e171e90c5044186e2198948
+size 55430656

onnx/vision_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d3e644416e543c62344c06f7dc8be5687633901a2931faccbe28688e30737e
+size 185947013

onnx/vision_model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae6e934667af50590c3d0ca69c7b14edc71f4df1b4f670e5ba6bc623495b691
+size 93973410

onnx/vision_model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a864016eff2d8829ec6088b1593c3c9e75a70e0413e0f02d4a4bbfddc3ef89d3
+size 61181030

onnx/vision_model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988c55937d35228f860bcc90742940ec3efe8d00054518249f6c82b66e1b4a7c
+size 53686874

onnx/vision_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1009cfce0eedd409f601e8351eedab72e8529641105eee6517821a9a634a2f4
+size 93973443

onnx/vision_model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1009cfce0eedd409f601e8351eedab72e8529641105eee6517821a9a634a2f4
+size 93973443

open_clip_config.json

@@ -0,0 +1,45 @@
+{
+  "model_cfg": {
+    "embed_dim": 768,
+    "init_logit_bias": -10,
+    "custom_text": true,
+    "vision_cfg": {
+      "image_size": 224,
+      "timm_model_name": "vit_base_patch16_siglip_224",
+      "timm_model_pretrained": false,
+      "timm_pool": "map",
+      "timm_proj": "none"
+    },
+    "text_cfg": {
+      "context_length": 64,
+      "vocab_size": 32000,
+      "hf_tokenizer_name": "timm/ViT-B-16-SigLIP",
+      "tokenizer_kwargs": {
+        "clean": "canonicalize"
+      },
+      "width": 768,
+      "heads": 12,
+      "layers": 12,
+      "no_causal_mask": true,
+      "proj_bias": true,
+      "pool_type": "last",
+      "norm_kwargs": {
+        "eps": 1e-06
+      }
+    }
+  },
+  "preprocess_cfg": {
+    "mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "interpolation": "bicubic",
+    "resize_mode": "squash"
+  }
+}

open_clip_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88908200434959fa3154ef79d408aac33341e8797fe5ca8ca6f0463aab32e6b3
+size 812658408

open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51a245681b2a027c26c1684a89dbd27cbd2819fca2fc2d4c697208d33d46400
+size 812750942

preprocessor_config.json

@@ -0,0 +1,27 @@
+{
+  "auto_map": {
+    "AutoProcessor": "marqo_fashionSigLIP.MarqoFashionSigLIPProcessor"
+	},
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_convert_rgb": true,
+  "image_processor_type": "SiglipImageProcessor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "marqo_fashionSigLIP.MarqoFashionSigLIPProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  },
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ]
+}

special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": true,
+    "single_word": false
+  }
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1,939 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<extra_id_99>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<extra_id_98>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<extra_id_97>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_96>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_95>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_94>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_93>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_92>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_91>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_90>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_89>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_88>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_87>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_86>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_85>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_84>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_83>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_82>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_81>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_80>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_79>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_78>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_77>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_76>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_75>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_74>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_73>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_72>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_71>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_70>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_69>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_68>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_67>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_66>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_65>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_64>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_63>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_62>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_61>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_60>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_59>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_58>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_57>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_56>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_55>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_54>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_53>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_52>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_51>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_50>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_49>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_47>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_46>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_45>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_44>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_43>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_42>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_41>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_40>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_39>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_38>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_37>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_36>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_35>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_34>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_33>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_32>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_31>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_30>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_29>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_28>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_27>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_26>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_25>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_24>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_23>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_22>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_21>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_20>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_19>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_18>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_17>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_16>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_15>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_14>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_13>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_12>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_11>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_10>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_9>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_8>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_7>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_6>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_5>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_4>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_3>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_2>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_1>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_0>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "legacy": false,
+  "model_max_length": 64,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}