update semantic

model/1_Pooling/config.json

@@ -0,0 +1,5 @@
+{
+    "embedding_dimension": 384,
+    "pooling_mode": "mean",
+    "include_prompt": true
+}

model/README.md

@@ -0,0 +1,156 @@
+---
+language:
+- multilingual
+- ar
+- bg
+- ca
+- cs
+- da
+- de
+- el
+- en
+- es
+- et
+- fa
+- fi
+- fr
+- gl
+- gu
+- he
+- hi
+- hr
+- hu
+- hy
+- id
+- it
+- ja
+- ka
+- ko
+- ku
+- lt
+- lv
+- mk
+- mn
+- mr
+- ms
+- my
+- nb
+- nl
+- pl
+- pt
+- ro
+- ru
+- sk
+- sl
+- sq
+- sr
+- sv
+- th
+- tr
+- uk
+- ur
+- vi
+license: apache-2.0
+library_name: sentence-transformers
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+language_bcp47:
+- fr-ca
+- pt-br
+- zh-cn
+- zh-tw
+pipeline_tag: sentence-similarity
+---
+
+# sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+# Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')
+model = AutoModel.from_pretrained('sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, max pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+
+This model was trained by [sentence-transformers](https://www.sbert.net/). 
+        
+If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
+```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 = "http://arxiv.org/abs/1908.10084",
+}
+```

model/config.json

@@ -0,0 +1,30 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

model/config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "pytorch": "2.10.0+cpu",
+    "sentence_transformers": "5.4.1",
+    "transformers": "5.0.0"
+  },
+  "default_prompt_name": null,
+  "model_type": "SentenceTransformer",
+  "prompts": {
+    "document": "",
+    "query": ""
+  },
+  "similarity_fn_name": "cosine"
+}

model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40576ad50be15cc77304f9f1404ba8e56aab722790ac98e01b0b03838e3639c4
+size 470637392

model/modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.base.modules.transformer.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.sentence_transformer.modules.pooling.Pooling"
+  }
+]

model/sentence_bert_config.json

@@ -0,0 +1,10 @@
+{
+    "transformer_task": "feature-extraction",
+    "modality_config": {
+        "text": {
+            "method": "forward",
+            "method_output_name": "last_hidden_state"
+        }
+    },
+    "module_output_name": "token_embeddings"
+}

model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad551d5600a84242d0973327029452a1e3672ba6313c2a3c3d69c4310e12719
+size 17082987

model/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "max_length": 128,
+  "model_max_length": 128,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

semantic_data.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4707fce720f2a563fc8d79d58dc61c6217386c1aee37a6f07346125b2fe79db0
-size 15883
+oid sha256:a51e6b74d082bdc05eb0776b2b6ee4d6ee422d41f2b13213a673957ee1f923be
+size 32659