upload files

.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

README-4.md

@@ -0,0 +1,117 @@
+---
+license: apache-2.0
+language:
+- ar
+pipeline_tag: text-classification
+tags:
+- transformers
+- sentence-transformers
+- text-embeddings-inference
+---
+
+# Introducing ARM-V1 | Arabic Reranker Model (Version 1)
+
+**For more info please refer to this blog: [ARM | Arabic Reranker Model](www.omarai.me).**
+
+✨ This model is designed specifically for Arabic language reranking tasks, optimized to handle queries and passages with precision. 
+
+✨ Unlike embedding models, which generate vector representations, this reranker directly evaluates the similarity between a question and a document, outputting a relevance score.
+
+✨ Trained on a combination of positive and hard negative query-passage pairs, it excels in identifying the most relevant results. 
+
+✨ The output score can be transformed into a [0, 1] range using a sigmoid function, providing a clear and interpretable measure of relevance.
+
+## Arabic RAG Pipeline 
+
+
+![Arabic RAG Pipeline](https://i.ibb.co/z4Fc3Kd/Screenshot-2024-11-28-at-10-17-39-AM.png)
+
+
+
+## Usage 
+### Using sentence-transformers
+
+```
+pip install sentence-transformers
+```
+```python
+from sentence_transformers import CrossEncoder
+
+# Load the cross-encoder model
+
+# Define a query and a set of candidates with varying degrees of relevance
+query = "تطبيقات الذكاء الاصطناعي تُستخدم في مختلف المجالات لتحسين الكفاءة."
+
+# Candidates with varying relevance to the query
+candidates = [
+    "الذكاء الاصطناعي يساهم في تحسين الإنتاجية في الصناعات المختلفة.", # Highly relevant
+    "نماذج التعلم الآلي يمكنها التعرف على الأنماط في مجموعات البيانات الكبيرة.", # Moderately relevant
+    "الذكاء الاصطناعي يساعد الأطباء في تحليل الصور الطبية بشكل أفضل.", # Somewhat relevant
+    "تستخدم الحيوانات التمويه كوسيلة للهروب من الحيوانات المفترسة.", # Irrelevant
+]
+
+# Create pairs of (query, candidate) for each candidate
+query_candidate_pairs = [(query, candidate) for candidate in candidates]
+
+# Get relevance scores from the model
+scores = model.predict(query_candidate_pairs)
+
+# Combine candidates with their scores and sort them by score in descending order (higher score = higher relevance)
+ranked_candidates = sorted(zip(candidates, scores), key=lambda x: x[1], reverse=True)
+
+# Output the ranked candidates with their scores
+print("Ranked candidates based on relevance to the query:")
+for i, (candidate, score) in enumerate(ranked_candidates, 1):
+    print(f"Rank {i}:")
+    print(f"Candidate: {candidate}")
+    print(f"Score: {score}\n")
+```
+## Evaluation 
+### Dataset
+
+Size: 3000 samples.
+
+### Structure:
+🔸 Query: A string representing the user's question.
+
+🔸 Candidate Document: A candidate passage to answer the query.
+
+🔸 Relevance Label: Binary label (1 for relevant, 0 for irrelevant).
+
+### Evaluation Process
+
+🔸 Query Grouping: Queries are grouped to evaluate the model's ability to rank candidate documents correctly for each query.
+
+🔸 Model Prediction: Each model predicts relevance scores for all candidate documents corresponding to a query.
+
+🔸 Metrics Calculation: Metrics are computed to measure how well the model ranks relevant documents higher than irrelevant ones.
+
+| Model                                     | MRR              | MAP              | nDCG@10          |
+|-------------------------------------------|------------------|------------------|------------------|
+| cross-encoder/ms-marco-MiniLM-L-6-v2      | 0.631 | 0.6313| 0.725 |
+| cross-encoder/ms-marco-MiniLM-L-12-v2     | 0.664 | 0.664 | 0.750 |
+| BAAI/bge-reranker-v2-m3                   | 0.902 | 0.902 | 0.927 |
+| Omartificial-Intelligence-Space/ARA-Reranker-V1 | **0.934**           | **0.9335**           | **0.951** |
+
+
+
+## <span style="color:blue">Acknowledgments</span>
+
+The author would like to thank Prince Sultan University for their invaluable support in this project. Their contributions and resources have been instrumental in the development and fine-tuning of these models.
+
+
+```markdown
+## Citation
+
+If you use the GATE, please cite it as follows:
+
+@misc{nacar2025ARM,
+      title={ARM, Arabic Reranker Model}, 
+      author={Omer Nacar},
+      year={2025},
+      url={https://huggingface.co/Omartificial-Intelligence-Space/ARA-Reranker-V1},
+}
+
+
+
+

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "BAAI/bge-reranker-v2-m3",
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

gitattributes.txt

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b5b844cc2e9151fb61a5beac039f722108a457381647a52a56a3374301dd244
+size 2271071852

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:cf44dabfaa82b1276a7af64a2ea2c76c047d560cf7bfb5711d6135382372c93d
+size 17083153

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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>",
+  "model_max_length": 8192,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}