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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+    "word_embedding_dimension": 1024,
+    "pooling_mode_cls_token": true,
+    "pooling_mode_mean_tokens": false,
+    "pooling_mode_max_tokens": false,
+    "pooling_mode_mean_sqrt_len_tokens": false,
+    "pooling_mode_weightedmean_tokens": false,
+    "pooling_mode_lasttoken": false,
+    "include_prompt": true
+}

README.md

@@ -0,0 +1,113 @@
+---
+language:
+- multilingual
+license: mit
+library_name: sentence-transformers
+tags:
+- claim2vec
+- embedding-model
+- fact-checking
+- claim-clustering
+- semantic-search
+- misinformation
+- contrastive-learning
+- multilingual-nlp
+---
+
+# 🧠 Claim2Vec
+
+**Claim2Vec** is a multilingual embedding model designed specifically for **fact-checked claim representation and clustering** in misinformation detection systems.
+
+It learns a semantic embedding space where recurrent and semantically equivalent claims are mapped close together, enabling improved grouping and retrieval of fact-checkable information across languages.
+
+---
+
+## 🎯 Motivation
+
+Recurrent claims are a major challenge for automated fact-checking systems, especially in multilingual environments. While existing approaches focus on pairwise claim matching, they often fail to capture global structures of semantically equivalent claims.
+
+Claim2Vec addresses this gap by learning embeddings optimized for **claim clustering**, enabling better organization of repeated misinformation narratives across datasets and languages.
+
+---
+
+## 🚀 Key Features
+
+- 🌍 Multilingual claim representation  
+- 🔗 Optimized for claim clustering tasks  
+- 🧠 Contrastive learning with semantically similar claim pairs  
+- 📊 Improved embedding geometry for cluster separation  
+- 🔄 Strong cross-lingual knowledge transfer  
+- ⚡ Designed for scalable fact-checking pipelines  
+
+---
+
+## 🧪 Training Objective
+
+Claim2Vec is trained using contrastive learning, encouraging semantically similar claims to have closer embeddings while pushing unrelated claims apart.
+
+---
+
+## 📊 Experimental Results
+
+Evaluation across:
+- 3 benchmark datasets  
+- 14 embedding baselines  
+- 7 clustering algorithms  
+
+shows that Claim2Vec consistently improves:
+- Cluster label alignment  
+- Embedding space structure  
+- Robustness across clustering configurations  
+
+---
+
+## 🌐 Multilingual Performance
+
+Claim2Vec demonstrates strong performance in multilingual settings, where clusters containing multiple languages benefit significantly from fine-tuning, indicating effective cross-lingual semantic transfer.
+
+---
+
+## 💡 Use Cases
+
+- Fact-checking systems  
+- Misinformation detection pipelines  
+- Claim deduplication  
+- Evidence grouping for RAG systems  
+- News verification tools  
+- Cross-lingual semantic clustering  
+
+---
+
+## 🧬 Usage
+
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer("your-username/claim2vec")
+
+claims = [
+    "COVID vaccines cause infertility",
+    "Studies show no link between COVID vaccines and infertility"
+]
+
+embeddings = model.encode(claims)
+print(embeddings.shape)
+```
+
+## 📄 Citation
+
+If you use Claim2Vec in your work, please cite:
+
+```bibtex
+@misc{claim2vec2026,
+  title={Claim2Vec: Embedding Fact-Check Claims for Multilingual Similarity and Clustering},
+  author={Panchendrarajan, Rrubaa and Zubiaga, Arkaitz},
+  year={2026},
+  eprint={2604.09812},
+  archivePrefix={arXiv},
+  primaryClass={cs.CL},
+  url={https://arxiv.org/abs/2604.09812}
+}
+```
+
+📄 arXiv: https://arxiv.org/abs/2604.09812

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "XLMRobertaModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 8194,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

config_sentence_transformers.json

@@ -0,0 +1,14 @@
+{
+  "__version__": {
+    "sentence_transformers": "5.1.1",
+    "transformers": "4.57.0",
+    "pytorch": "2.7.1+cu118"
+  },
+  "prompts": {
+    "query": "",
+    "document": ""
+  },
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine",
+  "model_type": "SentenceTransformer"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fd6e24a68c2ab38d47e1767d13c291807f886fd0be7b0f4dce52c728e632b71
+size 2271064456

modules.json

@@ -0,0 +1,20 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  },
+  {
+    "idx": 2,
+    "name": "2",
+    "path": "2_Normalize",
+    "type": "sentence_transformers.models.Normalize"
+  }
+]

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+    "max_seq_length": 512,
+    "do_lower_case": false
+}

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a6af42442a3e3e9f05f618eae0bb2d98ca4f6a6406cb80ef7a4fa865204d61
+size 17083052

tokenizer_config.json

@@ -0,0 +1,63 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}