Add new SentenceTransformer model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+0_Transformer/tokenizer.json filter=lfs diff=lfs merge=lfs -text

0_Transformer/config.json

@@ -0,0 +1,201 @@
+{
+  "_commit_hash": "4f4251a1ce7d8ead25533a658686f904866a24f2",
+  "_name_or_path": "jinaai/jina-clip-v2",
+  "add_projections": false,
+  "architectures": [
+    "JinaCLIPModel"
+  ],
+  "auto_map": {
+    "AutoConfig": "jinaai/jina-clip-implementation--configuration_clip.JinaCLIPConfig",
+    "AutoModel": "jinaai/jina-clip-implementation--modeling_clip.JinaCLIPModel"
+  },
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "matryoshka_dimensions": [
+    32,
+    64,
+    128,
+    256,
+    512,
+    768,
+    1024
+  ],
+  "model_type": "jina_clip",
+  "projection_dim": 1024,
+  "text_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "default_instruction_task": null,
+    "default_lora_task": "retrieval.query",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embed_dim": 1024,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hf_model_config_kwargs": {
+      "load_trained_adapters": false,
+      "lora_adaptations": [
+        "retrieval.query"
+      ],
+      "lora_alpha": 4,
+      "lora_dropout_p": 0.0,
+      "lora_main_params_trainable": false,
+      "lora_rank": 4,
+      "task_instructions": {
+        "retrieval.query": "Represent the query for retrieving evidence documents: "
+      },
+      "use_flash_attn": false
+    },
+    "hf_model_name_or_path": "jinaai/jina-embeddings-v3",
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "jina_clip_text",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "pooler_type": "mean_pooler",
+    "prefix": null,
+    "problem_type": null,
+    "proj_bias": false,
+    "proj_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.46.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "truncate_dim": null,
+  "use_text_flash_attn": false,
+  "use_vision_xformers": false,
+  "vision_config": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "drop_path_rate": 0.0,
+    "early_stopping": false,
+    "embed_dim": 1024,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "fused_layer_norm": false,
+    "head_width": 64,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 512,
+    "intp_freq": true,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layers": 24,
+    "length_penalty": 1.0,
+    "ls_init_value": null,
+    "max_length": 20,
+    "min_length": 0,
+    "mlp_ratio": 2.6667,
+    "model_type": "jina_clip_vision",
+    "naive_swiglu": true,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_dropout": 0.1,
+    "patch_size": 14,
+    "post_norm": false,
+    "prefix": null,
+    "problem_type": null,
+    "proj_type": null,
+    "pruned_heads": {},
+    "pt_hw_seq_len": 16,
+    "qkv_bias": true,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rope_embeddings": true,
+    "sep_token_id": null,
+    "subln": true,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.46.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "width": 1024,
+    "x_attention": false
+  }
+}

0_Transformer/custom_st.py

@@ -0,0 +1,272 @@
+import base64
+import json
+import os
+from io import BytesIO
+from typing import Any, Dict, List, Literal, Optional, Union
+
+import requests
+import torch
+from PIL import Image
+from torch import nn
+from transformers import AutoConfig, AutoImageProcessor, AutoModel, AutoTokenizer
+
+
+class Transformer(nn.Module):
+    def __init__(
+        self,
+        model_name_or_path: str = 'jinaai/jina-clip-v2',
+        tokenizer_name_or_path: Optional[str] = None,
+        image_processor_name_or_path: Optional[str] = None,
+        max_seq_length: Optional[int] = None,
+        config_args: Optional[Dict[str, Any]] = None,
+        model_args: Optional[Dict[str, Any]] = None,
+        tokenizer_args: Optional[Dict[str, Any]] = None,
+        image_processor_args: Optional[Dict[str, Any]] = None,
+        assume_text_inputs: bool = False,
+        cache_dir: Optional[str] = None,
+        backend: Literal['torch', 'onnx', 'openvino'] = 'torch',
+        **_,
+    ) -> None:
+        """
+        Creates a custom SentenceTransformer module that uses `jinai/jina-clip-v2` to
+        map sentences/images to embeddings
+
+        Args:
+            model_name_or_path (str, optional): If it is a filepath on disc, it loads
+                the model from that path. If it is not a path, tries to construct a
+                model from the Hugging Face Hub with that name. Defaults to
+                'jinaai/jina-clip-v2'
+            tokenizer_name_or_path (str, optional): If it is a filepath on disc, it
+                loads the tokenizer from that path. If it is not a path, tries to
+                construct a tokenizer from the Hugging Face Hub with that name.
+                If `None` it is automatically set to the value of `model_name_or_path`
+            image_processor_name_or_path (str, optional): If it is a filepath on disc,
+                it loads the image processor from that path. If it is not a path, tries
+                to construct an image processor from the Hugging Face Hub with that
+                name. If `None` it is automatically set to the value of
+                `model_name_or_path`
+            max_seq_length (int, optional): The maximum sequence length of the model.
+                If not provided, will be inferred from model or tokenizer
+            config_args (Dict[str, Any], optional): Additional model configuration
+                parameters to be passed to the Hugging Face Transformers config
+            model_args (Dict[str, Any], optional): Additional model configuration
+                parameters to be passed to the Hugging Face Transformers model
+            tokenizer_args (Dict[str, Any], optional): Additional tokenizer
+                configuration parameters to be passed to the Hugging Face Transformers
+                tokenizer
+            image_processor_args (Dict[str, Any], optional): Additional image processor
+                configuration parameters to be passed to the Hugging Face Transformers
+                image processor
+            assume_text_inputs (bool, optional): If set to `True`, all inputs are
+                treated as texts. Defaults to `False`
+            cache_dir (str, optional): The Hugging Face Hub cache directory
+            backend (str, optional): Computational backend, only 'torch' is supported
+
+        Example:
+            ::
+
+                from sentence_transformers import SentenceTransformer
+
+                model = SentenceTransformer(
+                    'jinaai/jina-clip-v2', trust_remote_code=True
+                )
+                sentences_or_images = [
+                    "The weather is lovely today.",
+                    "It's so sunny outside!",
+                    "/path/to/stadium.jpg",
+                ]
+                embeddings = model.encode(sentences_or_images)
+                print(embeddings.shape)
+                # (3, 1024)
+
+                # Get the similarity scores between all inputs
+                similarities = model.similarity(embeddings, embeddings)
+                print(similarities)
+                # tensor([[1.0000, 0.6817, 0.0492],
+                #         [0.6817, 1.0000, 0.0421],
+                #         [0.0492, 0.0421, 1.0000]])
+        """
+        super(Transformer, self).__init__()
+        if backend != 'torch':
+            raise ValueError(
+                f'Backend \'{backend}\' is not supported, please use \'torch\' instead'
+            )
+
+        config_kwargs = config_args or {}
+        model_kwargs = model_args or {}
+        tokenizer_kwargs = tokenizer_args or {}
+        image_processor_kwargs = {
+            'token': model_kwargs.get('token', None),
+            'trust_remote_code': model_kwargs.get('trust_remote_code', False),
+            'revision': model_kwargs.get('revision', None),
+            'local_files_only': model_kwargs.get('local_files_only', None),
+        }
+        image_processor_kwargs.update(image_processor_args or {})
+
+        config = AutoConfig.from_pretrained(
+            model_name_or_path, cache_dir=cache_dir, **config_kwargs
+        )
+        self.model = AutoModel.from_pretrained(
+            model_name_or_path, config=config, cache_dir=cache_dir, **model_kwargs
+        )
+        if max_seq_length is not None and 'model_max_length' not in tokenizer_kwargs:
+            tokenizer_kwargs['model_max_length'] = max_seq_length
+
+        self.tokenizer = AutoTokenizer.from_pretrained(
+            tokenizer_name_or_path or model_name_or_path,
+            cache_dir=cache_dir,
+            **tokenizer_kwargs,
+        )
+        self.image_processor = AutoImageProcessor.from_pretrained(
+            image_processor_name_or_path or model_name_or_path,
+            cache_dir=cache_dir,
+            **image_processor_kwargs,
+        )
+        self.assume_text_inputs = assume_text_inputs
+
+        # No max_seq_length set. Try to infer from model
+        if max_seq_length is None:
+            if (
+                hasattr(self.model, 'config')
+                and hasattr(self.model.config, 'max_position_embeddings')
+                and hasattr(self.tokenizer, 'model_max_length')
+            ):
+                max_seq_length = min(
+                    self.model.config.max_position_embeddings,
+                    self.tokenizer.model_max_length,
+                )
+        self.max_seq_length = max_seq_length
+        if tokenizer_name_or_path is not None:
+            self.model.config.tokenizer_class = self.tokenizer.__class__.__name__
+
+    @staticmethod
+    def _decode_data_image(data_image_str: str) -> Image.Image:
+        header, data = data_image_str.split(',', 1)
+        image_data = base64.b64decode(data)
+        return Image.open(BytesIO(image_data))
+
+    def tokenize(
+        self, texts: List[Union[str, Image.Image]], padding: Union[str, bool] = True
+    ) -> Dict[str, torch.Tensor]:
+        """
+        Encodes input samples. Text samples are tokenized. Image URLs, image data
+        buffers and PIL images are passed through the image processor.
+        """
+        _images = []
+        _texts = []
+        _image_or_text_descriptors = []
+
+        if self.assume_text_inputs:
+            for sample in texts:
+                if isinstance(sample, str):
+                    _texts.append(sample)
+                    _image_or_text_descriptors.append(1)
+        else:
+            for sample in texts:
+                if isinstance(sample, str):
+                    if sample.startswith('http'):
+                        try:
+                            response = requests.get(sample)
+                            _images.append(
+                                Image.open(BytesIO(response.content)).convert('RGB')
+                            )
+                            _image_or_text_descriptors.append(0)
+                        except Exception as e:
+                            _ = str(e)
+                            _texts.append(sample)
+                            _image_or_text_descriptors.append(1)
+                    elif sample.startswith('data:image/'):
+                        _images.append(self._decode_data_image(sample).convert('RGB'))
+                        _image_or_text_descriptors.append(0)
+                    else:
+                        try:
+                            _images.append(Image.open(sample).convert('RGB'))
+                            _image_or_text_descriptors.append(0)
+                        except Exception as e:
+                            _ = str(e)
+                            _texts.append(sample)
+                            _image_or_text_descriptors.append(1)
+                elif isinstance(sample, Image.Image):
+                    _images.append(sample.convert('RGB'))
+                    _image_or_text_descriptors.append(0)
+
+        encoding = {}
+        if len(_texts):
+            encoding['input_ids'] = self.tokenizer(
+                _texts,
+                padding=padding,
+                truncation='longest_first',
+                return_tensors='pt',
+                max_length=self.max_seq_length,
+            ).input_ids
+
+        if len(_images):
+            encoding['pixel_values'] = self.image_processor(
+                _images, return_tensors='pt'
+            ).pixel_values
+
+        encoding['image_text_info'] = _image_or_text_descriptors
+        return encoding
+
+    def forward(self, features: Dict[str, torch.Tensor]) -> Dict[str, torch.Tensor]:
+        image_embeddings = []
+        text_embeddings = []
+
+        if 'pixel_values' in features:
+            image_embeddings = self.model.get_image_features(features['pixel_values'])
+        if 'input_ids' in features:
+            text_embeddings = self.model.get_text_features(features['input_ids'])
+
+        sentence_embedding = []
+        image_features = iter(image_embeddings)
+        text_features = iter(text_embeddings)
+        for _, _input_type in enumerate(features['image_text_info']):
+            if _input_type == 0:
+                sentence_embedding.append(next(image_features))
+            else:
+                sentence_embedding.append(next(text_features))
+
+        features['sentence_embedding'] = torch.stack(sentence_embedding).float()
+        return features
+
+    def save(self, output_path: str, safe_serialization: bool = True) -> None:
+        self.model.save_pretrained(output_path, safe_serialization=safe_serialization)
+        self.tokenizer.save_pretrained(output_path)
+        self.image_processor.save_pretrained(output_path)
+
+    @staticmethod
+    def load(input_path: str) -> 'Transformer':
+        # Old classes used other config names than 'sentence_bert_config.json'
+        for config_name in [
+            'sentence_bert_config.json',
+            'sentence_roberta_config.json',
+            'sentence_distilbert_config.json',
+            'sentence_camembert_config.json',
+            'sentence_albert_config.json',
+            'sentence_xlm-roberta_config.json',
+            'sentence_xlnet_config.json',
+        ]:
+            sbert_config_path = os.path.join(input_path, config_name)
+            if os.path.exists(sbert_config_path):
+                break
+
+        with open(sbert_config_path) as fIn:
+            config = json.load(fIn)
+
+        # Don't allow configs to set trust_remote_code
+        if 'config_kwargs' in config and 'trust_remote_code' in config['config_kwargs']:
+            config['config_kwargs'].pop('trust_remote_code')
+        if 'model_kwargs' in config and 'trust_remote_code' in config['model_kwargs']:
+            config['model_kwargs'].pop('trust_remote_code')
+        if (
+            'tokenizer_kwargs' in config
+            and 'trust_remote_code' in config['tokenizer_kwargs']
+        ):
+            config['tokenizer_kwargs'].pop('trust_remote_code')
+        if (
+            'image_processor_kwargs' in config
+            and 'trust_remote_code' in config['image_processor_kwargs']
+        ):
+            config['image_processor_kwargs'].pop('trust_remote_code')
+
+        return Transformer(model_name_or_path=input_path, **config)

0_Transformer/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58e5dff44bee390193eeb733f543008b6f2fb5779c58073881785b03097788e9
+size 3461246364

0_Transformer/preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "auto_map": {
+    "AutoImageProcessor": "jinaai/jina-clip-implementation--processing_clip.JinaCLIPImageProcessor",
+    "AutoProcessor": "jinaai/jina-clip-implementation--processing_clip.JinaCLIPProcessor"
+  },
+  "fill_color": 0,
+  "image_processor_type": "JinaCLIPImageProcessor",
+  "interpolation": "bicubic",
+  "mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "processor_class": "JinaCLIPProcessor",
+  "resize_mode": "shortest",
+  "size": 512,
+  "std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ]
+}

0_Transformer/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

0_Transformer/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e19cd8c08f528b481e909f73dbd1fd62b1e8b1117579ba205e477801237f9e0
+size 17082988

0_Transformer/tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 77,
+  "model_max_length": 8194,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

README.md

@@ -0,0 +1,552 @@
+---
+base_model: jinaai/jina-clip-v2
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- dataset_size:63802
+- loss:CoSENTLoss
+widget:
+- source_sentence: машинка детская самоходная бибикар желтый
+  sentences:
+  - 'машинка детская красная бибикар '
+  - моторное масло alpine dx1 5w 30 5л 0101662
+  - 'спинбайк schwinn ic7 '
+- source_sentence: 'велосипед stels saber 20 фиолетовый '
+  sentences:
+  - 'детские спортивные комплексы '
+  - 'велосипед bmx stels saber 20 v010 2020 '
+  - 50218 кабель ugreen hd132 hdmi zinc alloy optical fiber cable черный 40m
+- source_sentence: гидравличесские прессы
+  sentences:
+  - пресс гидравлический ручной механизмом
+  - ракетка для настольного тенниса fora 7
+  - 'объектив panasonic 20mm f1 7 asph ii h h020ae k '
+- source_sentence: 'бокс пластиковый монтажной платой щмп п 300х200х130 мм ip65 proxima
+    ящики щитки шкафы '
+  sentences:
+  - батарейный отсек для 4xаа открытый проволочные выводы разъем dcx2 1 battery holder
+    4xaa 6v dc
+  - 'bugera bc15 '
+  - 'бокс пластиковый монтажной платой щмп п 500х350х190 мм ip65 proxima ящики щитки
+    шкафы '
+- source_sentence: 'honor watch gs pro black '
+  sentences:
+  - 'honor watch gs pro white '
+  - трансформер pituso carlo hb gy 06 lemon
+  - 'электровелосипед колхозник volten greenline 500w '
+model-index:
+- name: SentenceTransformer based on jinaai/jina-clip-v2
+  results:
+  - task:
+      type: semantic-similarity
+      name: Semantic Similarity
+    dataset:
+      name: example dev
+      type: example-dev
+    metrics:
+    - type: pearson_cosine
+      value: 0.46018545926876964
+      name: Pearson Cosine
+    - type: spearman_cosine
+      value: 0.4873837299726027
+      name: Spearman Cosine
+---
+
+# SentenceTransformer based on jinaai/jina-clip-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [jinaai/jina-clip-v2](https://huggingface.co/jinaai/jina-clip-v2). It maps sentences & paragraphs to a None-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
+
+## Model Details
+
+### Model Description
+- **Model Type:** Sentence Transformer
+- **Base model:** [jinaai/jina-clip-v2](https://huggingface.co/jinaai/jina-clip-v2) <!-- at revision 4f4251a1ce7d8ead25533a658686f904866a24f2 -->
+- **Maximum Sequence Length:** None tokens
+- **Output Dimensionality:** None dimensions
+- **Similarity Function:** Cosine Similarity
+<!-- - **Training Dataset:** Unknown -->
+<!-- - **Language:** Unknown -->
+<!-- - **License:** Unknown -->
+
+### Model Sources
+
+- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
+- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
+- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (transformer): Transformer(
+    (model): JinaCLIPModel(
+      (text_model): HFTextEncoder(
+        (transformer): XLMRobertaLoRA(
+          (roberta): XLMRobertaModel(
+            (embeddings): XLMRobertaEmbeddings(
+              (word_embeddings): ParametrizedEmbedding(
+                250002, 1024, padding_idx=1
+                (parametrizations): ModuleDict(
+                  (weight): ParametrizationList(
+                    (0): LoRAParametrization()
+                  )
+                )
+              )
+              (token_type_embeddings): ParametrizedEmbedding(
+                1, 1024
+                (parametrizations): ModuleDict(
+                  (weight): ParametrizationList(
+                    (0): LoRAParametrization()
+                  )
+                )
+              )
+            )
+            (emb_drop): Dropout(p=0.1, inplace=False)
+            (emb_ln): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+            (encoder): XLMRobertaEncoder(
+              (layers): ModuleList(
+                (0-23): 24 x Block(
+                  (mixer): MHA(
+                    (rotary_emb): RotaryEmbedding()
+                    (Wqkv): ParametrizedLinearResidual(
+                      in_features=1024, out_features=3072, bias=True
+                      (parametrizations): ModuleDict(
+                        (weight): ParametrizationList(
+                          (0): LoRAParametrization()
+                        )
+                      )
+                    )
+                    (inner_attn): SelfAttention(
+                      (drop): Dropout(p=0.1, inplace=False)
+                    )
+                    (inner_cross_attn): CrossAttention(
+                      (drop): Dropout(p=0.1, inplace=False)
+                    )
+                    (out_proj): ParametrizedLinear(
+                      in_features=1024, out_features=1024, bias=True
+                      (parametrizations): ModuleDict(
+                        (weight): ParametrizationList(
+                          (0): LoRAParametrization()
+                        )
+                      )
+                    )
+                  )
+                  (dropout1): Dropout(p=0.1, inplace=False)
+                  (drop_path1): StochasticDepth(p=0.0, mode=row)
+                  (norm1): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+                  (mlp): Mlp(
+                    (fc1): ParametrizedLinear(
+                      in_features=1024, out_features=4096, bias=True
+                      (parametrizations): ModuleDict(
+                        (weight): ParametrizationList(
+                          (0): LoRAParametrization()
+                        )
+                      )
+                    )
+                    (fc2): ParametrizedLinear(
+                      in_features=4096, out_features=1024, bias=True
+                      (parametrizations): ModuleDict(
+                        (weight): ParametrizationList(
+                          (0): LoRAParametrization()
+                        )
+                      )
+                    )
+                  )
+                  (dropout2): Dropout(p=0.1, inplace=False)
+                  (drop_path2): StochasticDepth(p=0.0, mode=row)
+                  (norm2): LayerNorm((1024,), eps=1e-05, elementwise_affine=True)
+                )
+              )
+            )
+          )
+        )
+        (pooler): MeanPooler()
+        (proj): Identity()
+      )
+      (vision_model): EVAVisionTransformer(
+        (patch_embed): PatchEmbed(
+          (proj): Conv2d(3, 1024, kernel_size=(14, 14), stride=(14, 14))
+        )
+        (pos_drop): Dropout(p=0.0, inplace=False)
+        (rope): VisionRotaryEmbeddingFast()
+        (blocks): ModuleList(
+          (0-23): 24 x Block(
+            (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+            (attn): Attention(
+              (q_proj): Linear(in_features=1024, out_features=1024, bias=False)
+              (k_proj): Linear(in_features=1024, out_features=1024, bias=False)
+              (v_proj): Linear(in_features=1024, out_features=1024, bias=False)
+              (attn_drop): Dropout(p=0.0, inplace=False)
+              (inner_attn_ln): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+              (proj): Linear(in_features=1024, out_features=1024, bias=True)
+              (proj_drop): Dropout(p=0.0, inplace=False)
+              (rope): VisionRotaryEmbeddingFast()
+            )
+            (drop_path): Identity()
+            (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+            (mlp): SwiGLU(
+              (w1): Linear(in_features=1024, out_features=2730, bias=True)
+              (w2): Linear(in_features=1024, out_features=2730, bias=True)
+              (act): SiLU()
+              (ffn_ln): LayerNorm((2730,), eps=1e-06, elementwise_affine=True)
+              (w3): Linear(in_features=2730, out_features=1024, bias=True)
+              (drop): Dropout(p=0.0, inplace=False)
+            )
+          )
+        )
+        (norm): LayerNorm((1024,), eps=1e-06, elementwise_affine=True)
+        (head): Identity()
+        (patch_dropout): PatchDropout()
+      )
+      (visual_projection): Identity()
+      (text_projection): Identity()
+    )
+  )
+  (normalizer): Normalize()
+)
+```
+
+## Usage
+
+### Direct Usage (Sentence Transformers)
+
+First install the Sentence Transformers library:
+
+```bash
+pip install -U sentence-transformers
+```
+
+Then you can load this model and run inference.
+```python
+from sentence_transformers import SentenceTransformer
+
+# Download from the 🤗 Hub
+model = SentenceTransformer("seregadgl/t12")
+# Run inference
+sentences = [
+    'honor watch gs pro black ',
+    'honor watch gs pro white ',
+    'трансформер pituso carlo hb gy 06 lemon',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 1024]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+<!--
+### Direct Usage (Transformers)
+
+<details><summary>Click to see the direct usage in Transformers</summary>
+
+</details>
+-->
+
+<!--
+### Downstream Usage (Sentence Transformers)
+
+You can finetune this model on your own dataset.
+
+<details><summary>Click to expand</summary>
+
+</details>
+-->
+
+<!--
+### Out-of-Scope Use
+
+*List how the model may foreseeably be misused and address what users ought not to do with the model.*
+-->
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Dataset: `example-dev`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | Value      |
+|:--------------------|:-----------|
+| pearson_cosine      | 0.4602     |
+| **spearman_cosine** | **0.4874** |
+
+<!--
+## Bias, Risks and Limitations
+
+*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
+-->
+
+<!--
+### Recommendations
+
+*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
+-->
+
+## Training Details
+
+### Training Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 63,802 training samples
+* Columns: <code>doc</code>, <code>candidate</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | doc                                                                                            | candidate                                                                                      | label                                           |
+  |:--------|:-----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                                         | string                                                                                         | int                                             |
+  | details | <ul><li>min: 5 characters</li><li>mean: 40.56 characters</li><li>max: 115 characters</li></ul> | <ul><li>min: 4 characters</li><li>mean: 40.11 characters</li><li>max: 115 characters</li></ul> | <ul><li>0: ~85.20%</li><li>1: ~14.80%</li></ul> |
+* Samples:
+  | doc                                                    | candidate                                                              | label          |
+  |:-------------------------------------------------------|:-----------------------------------------------------------------------|:---------------|
+  | <code>массажер xiaomi massage gun eu bhr5608eu </code> | <code>перкуссионный массажер xiaomi massage gun mini bhr6083gl </code> | <code>0</code> |
+  | <code>безударная дрель ingco ed50028 </code>           | <code>ударная дрель ingco id211002 </code>                             | <code>0</code> |
+  | <code>жидкость old smuggler 30мл 20мг </code>          | <code>жидкость old smuggler salt 30ml marlboro 20mg</code>             | <code>0</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Evaluation Dataset
+
+#### Unnamed Dataset
+
+
+* Size: 7,090 evaluation samples
+* Columns: <code>doc</code>, <code>candidate</code>, and <code>label</code>
+* Approximate statistics based on the first 1000 samples:
+  |         | doc                                                                                            | candidate                                                                                      | label                                           |
+  |:--------|:-----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|:------------------------------------------------|
+  | type    | string                                                                                         | string                                                                                         | int                                             |
+  | details | <ul><li>min: 4 characters</li><li>mean: 40.68 characters</li><li>max: 198 characters</li></ul> | <ul><li>min: 5 characters</li><li>mean: 39.92 characters</li><li>max: 178 characters</li></ul> | <ul><li>0: ~84.20%</li><li>1: ~15.80%</li></ul> |
+* Samples:
+  | doc                                                                                                           | candidate                                                                                                    | label          |
+  |:--------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:---------------|
+  | <code>круглое пляжное парео селфи коврик пляжная подстилка пляжное покрывало пляжный коврик пироженко </code> | <code>круглое п��яжное парео селфи коврик пляжная подстилка пляжное покрывало пляжный коврик клубника </code> | <code>0</code> |
+  | <code>аккумулятор батарея для ноутбука asus g751 </code>                                                      | <code>аккумулятор батарея для ноутбука asus g75 series</code>                                                | <code>0</code> |
+  | <code>миксер bosch mfq3520 mfq 3520 </code>                                                                   | <code>миксер bosch mfq 4020 </code>                                                                          | <code>0</code> |
+* Loss: [<code>CoSENTLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosentloss) with these parameters:
+  ```json
+  {
+      "scale": 20.0,
+      "similarity_fct": "pairwise_cos_sim"
+  }
+  ```
+
+### Training Hyperparameters
+#### Non-Default Hyperparameters
+
+- `eval_strategy`: steps
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `learning_rate`: 2e-05
+- `num_train_epochs`: 1
+- `lr_scheduler_type`: cosine
+- `warmup_ratio`: 0.1
+- `load_best_model_at_end`: True
+- `batch_sampler`: no_duplicates
+
+#### All Hyperparameters
+<details><summary>Click to expand</summary>
+
+- `overwrite_output_dir`: False
+- `do_predict`: False
+- `eval_strategy`: steps
+- `prediction_loss_only`: True
+- `per_device_train_batch_size`: 16
+- `per_device_eval_batch_size`: 16
+- `per_gpu_train_batch_size`: None
+- `per_gpu_eval_batch_size`: None
+- `gradient_accumulation_steps`: 1
+- `eval_accumulation_steps`: None
+- `torch_empty_cache_steps`: None
+- `learning_rate`: 2e-05
+- `weight_decay`: 0.0
+- `adam_beta1`: 0.9
+- `adam_beta2`: 0.999
+- `adam_epsilon`: 1e-08
+- `max_grad_norm`: 1.0
+- `num_train_epochs`: 1
+- `max_steps`: -1
+- `lr_scheduler_type`: cosine
+- `lr_scheduler_kwargs`: {}
+- `warmup_ratio`: 0.1
+- `warmup_steps`: 0
+- `log_level`: passive
+- `log_level_replica`: warning
+- `log_on_each_node`: True
+- `logging_nan_inf_filter`: True
+- `save_safetensors`: True
+- `save_on_each_node`: False
+- `save_only_model`: False
+- `restore_callback_states_from_checkpoint`: False
+- `no_cuda`: False
+- `use_cpu`: False
+- `use_mps_device`: False
+- `seed`: 42
+- `data_seed`: None
+- `jit_mode_eval`: False
+- `use_ipex`: False
+- `bf16`: False
+- `fp16`: False
+- `fp16_opt_level`: O1
+- `half_precision_backend`: auto
+- `bf16_full_eval`: False
+- `fp16_full_eval`: False
+- `tf32`: None
+- `local_rank`: 0
+- `ddp_backend`: None
+- `tpu_num_cores`: None
+- `tpu_metrics_debug`: False
+- `debug`: []
+- `dataloader_drop_last`: False
+- `dataloader_num_workers`: 0
+- `dataloader_prefetch_factor`: None
+- `past_index`: -1
+- `disable_tqdm`: False
+- `remove_unused_columns`: True
+- `label_names`: None
+- `load_best_model_at_end`: True
+- `ignore_data_skip`: False
+- `fsdp`: []
+- `fsdp_min_num_params`: 0
+- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
+- `fsdp_transformer_layer_cls_to_wrap`: None
+- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
+- `deepspeed`: None
+- `label_smoothing_factor`: 0.0
+- `optim`: adamw_torch
+- `optim_args`: None
+- `adafactor`: False
+- `group_by_length`: False
+- `length_column_name`: length
+- `ddp_find_unused_parameters`: None
+- `ddp_bucket_cap_mb`: None
+- `ddp_broadcast_buffers`: False
+- `dataloader_pin_memory`: True
+- `dataloader_persistent_workers`: False
+- `skip_memory_metrics`: True
+- `use_legacy_prediction_loop`: False
+- `push_to_hub`: False
+- `resume_from_checkpoint`: None
+- `hub_model_id`: None
+- `hub_strategy`: every_save
+- `hub_private_repo`: False
+- `hub_always_push`: False
+- `gradient_checkpointing`: False
+- `gradient_checkpointing_kwargs`: None
+- `include_inputs_for_metrics`: False
+- `include_for_metrics`: []
+- `eval_do_concat_batches`: True
+- `fp16_backend`: auto
+- `push_to_hub_model_id`: None
+- `push_to_hub_organization`: None
+- `mp_parameters`: 
+- `auto_find_batch_size`: False
+- `full_determinism`: False
+- `torchdynamo`: None
+- `ray_scope`: last
+- `ddp_timeout`: 1800
+- `torch_compile`: False
+- `torch_compile_backend`: None
+- `torch_compile_mode`: None
+- `dispatch_batches`: None
+- `split_batches`: None
+- `include_tokens_per_second`: False
+- `include_num_input_tokens_seen`: False
+- `neftune_noise_alpha`: None
+- `optim_target_modules`: None
+- `batch_eval_metrics`: False
+- `eval_on_start`: False
+- `use_liger_kernel`: False
+- `eval_use_gather_object`: False
+- `average_tokens_across_devices`: False
+- `prompts`: None
+- `batch_sampler`: no_duplicates
+- `multi_dataset_batch_sampler`: proportional
+
+</details>
+
+### Training Logs
+| Epoch  | Step | Training Loss | Validation Loss | example-dev_spearman_cosine |
+|:------:|:----:|:-------------:|:---------------:|:---------------------------:|
+| 0      | 0    | -             | -               | 0.0849                      |
+| 0.1254 | 500  | 3.7498        | 3.0315          | 0.3797                      |
+| 0.2508 | 1000 | 2.7653        | 2.7538          | 0.4508                      |
+| 0.3761 | 1500 | 2.5938        | 2.7853          | 0.4689                      |
+| 0.5015 | 2000 | 2.6425        | 2.6761          | 0.4800                      |
+| 0.6269 | 2500 | 2.6859        | 2.6341          | 0.4840                      |
+| 0.7523 | 3000 | 2.5805        | 2.6350          | 0.4855                      |
+| 0.8776 | 3500 | 2.7247        | 2.6087          | 0.4874                      |
+
+
+### Framework Versions
+- Python: 3.10.14
+- Sentence Transformers: 3.3.1
+- Transformers: 4.46.3
+- PyTorch: 2.4.0
+- Accelerate: 0.34.2
+- Datasets: 3.0.1
+- Tokenizers: 0.20.0
+
+## Citation
+
+### BibTeX
+
+#### Sentence Transformers
+```bibtex
+@inproceedings{reimers-2019-sentence-bert,
+    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
+    author = "Reimers, Nils and Gurevych, Iryna",
+    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
+    month = "11",
+    year = "2019",
+    publisher = "Association for Computational Linguistics",
+    url = "https://arxiv.org/abs/1908.10084",
+}
+```
+
+#### CoSENTLoss
+```bibtex
+@online{kexuefm-8847,
+    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
+    author={Su Jianlin},
+    year={2022},
+    month={Jan},
+    url={https://kexue.fm/archives/8847},
+}
+```
+
+<!--
+## Glossary
+
+*Clearly define terms in order to be accessible across audiences.*
+-->
+
+<!--
+## Model Card Authors
+
+*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
+-->
+
+<!--
+## Model Card Contact
+
+*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
+-->

config_sentence_transformers.json

@@ -0,0 +1,12 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.3.1",
+    "transformers": "4.46.3",
+    "pytorch": "2.4.0"
+  },
+  "prompts": {
+    "retrieval.query": "Represent the query for retrieving evidence documents: "
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "transformer",
+    "path": "0_Transformer",
+    "type": "custom_st.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "normalizer",
+    "path": "1_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]