Upload folder using huggingface_hub

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/aws.xml

@@ -0,0 +1,11 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="accountSettings">
+    <option name="activeRegion" value="us-east-1" />
+    <option name="recentlyUsedRegions">
+      <list>
+        <option value="us-east-1" />
+      </list>
+    </option>
+  </component>
+</project>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.12 (pythonProject)" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.12 (pythonProject)" project-jdk-type="Python SDK" />
+</project>

.idea/modernbert_mlm_sts.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/modernbert_mlm_sts.iml" filepath="$PROJECT_DIR$/.idea/modernbert_mlm_sts.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

.idea/workspace.xml

@@ -0,0 +1,58 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="AutoImportSettings">
+    <option name="autoReloadType" value="SELECTIVE" />
+  </component>
+  <component name="ChangeListManager">
+    <list default="true" id="59391769-f550-47d2-b479-30410ad79396" name="Changes" comment="">
+      <change beforePath="$PROJECT_DIR$/README.md" beforeDir="false" afterPath="$PROJECT_DIR$/README.md" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/config.json" beforeDir="false" afterPath="$PROJECT_DIR$/config.json" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/optimizer.pt" beforeDir="false" />
+      <change beforePath="$PROJECT_DIR$/rng_state.pth" beforeDir="false" />
+      <change beforePath="$PROJECT_DIR$/scaler.pt" beforeDir="false" />
+      <change beforePath="$PROJECT_DIR$/scheduler.pt" beforeDir="false" />
+      <change beforePath="$PROJECT_DIR$/trainer_state.json" beforeDir="false" />
+      <change beforePath="$PROJECT_DIR$/training_args.bin" beforeDir="false" />
+    </list>
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="Git.Settings">
+    <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
+  </component>
+  <component name="ProjectColorInfo"><![CDATA[{
+  "associatedIndex": 8
+}]]></component>
+  <component name="ProjectId" id="2u5uX6wr1oiVSfgNfNopm0F96iP" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent"><![CDATA[{
+  "keyToString": {
+    "RunOnceActivity.ShowReadmeOnStart": "true",
+    "git-widget-placeholder": "main",
+    "last_opened_file_path": "/Users/omarelshehy/modernbert_mlm_sts"
+  }
+}]]></component>
+  <component name="SharedIndexes">
+    <attachedChunks>
+      <set>
+        <option value="bundled-python-sdk-abccbe9d933a-ba05f1cad1b1-com.jetbrains.pycharm.community.sharedIndexes.bundled-PC-242.20224.428" />
+      </set>
+    </attachedChunks>
+  </component>
+  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="59391769-f550-47d2-b479-30410ad79396" name="Changes" comment="" />
+      <created>1741550792489</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1741550792489</updated>
+    </task>
+    <servers />
+  </component>
+</project>

1_Pooling/config.json

@@ -0,0 +1,10 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "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

@@ -1,3 +1,190 @@
----
-license: apache-2.0
----
+---
+tags:
+- sentence-transformers
+- sentence-similarity
+- feature-extraction
+- generated_from_trainer
+- loss:MultipleNegativesRankingLoss
+- mteb
+base_model: NAMAA-Space/AraModernBert-Base-V1.0
+pipeline_tag: sentence-similarity
+library_name: sentence-transformers
+metrics:
+- pearson_cosine
+- spearman_cosine
+model-index:
+- name: NAMAA-Space/AraModernBert-Base-V1.0
+  results:
+  - dataset:
+      config: ar-ar
+      name: MTEB STS17 (ar-ar)
+      revision: faeb762787bd10488a50c8b5be4a3b82e411949c
+      split: test
+      type: mteb/sts17-crosslingual-sts
+    metrics:
+    - type: pearson
+      value: 82.4888
+    - type: spearman
+      value: 83.0981
+    - type: cosine_pearson
+      value: 82.4888
+    - type: cosine_spearman
+      value: 83.1109
+    - type: manhattan_pearson
+      value: 81.2051
+    - type: manhattan_spearman
+      value: 83.0197
+    - type: euclidean_pearson
+      value: 81.1013
+    - type: euclidean_spearman
+      value: 82.8922
+    - type: main_score
+      value: 83.1109
+    task:
+      type: STS
+  - dataset:
+      config: ar
+      name: MTEB STS22.v2 (ar)
+      revision: d31f33a128469b20e357535c39b82fb3c3f6f2bd
+      split: test
+      type: mteb/sts22-crosslingual-sts
+    metrics:
+    - type: pearson
+      value: 52.58540000000001
+    - type: spearman
+      value: 61.7371
+    - type: cosine_pearson
+      value: 52.58540000000001
+    - type: cosine_spearman
+      value: 61.7371
+    - type: manhattan_pearson
+      value: 55.887299999999996
+    - type: manhattan_spearman
+      value: 61.3654
+    - type: euclidean_pearson
+      value: 55.633500000000005
+    - type: euclidean_spearman
+      value: 61.2124
+    - type: main_score
+      value: 61.7371
+    task:
+      type: STS
+---
+
+# SentenceTransformer based on NAMAA-Space/AraModernBert-Base-V1.0
+
+This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [NAMAA-Space/AraModernBert-Base-V1.0](https://huggingface.co/NAMAA-Space/AraModernBert-Base-V1.0) . It maps sentences & paragraphs to a 768-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:** [NAMAA-Space/AraModernBert-Base-V1.0](https://huggingface.co/NAMAA-Space/AraModernBert-Base-V1.0) <!-- at revision b2db86686c6c03497db32a63187be8954cc34013 -->
+- **Maximum Sequence Length:** 512 tokens
+- **Output Dimensionality:** 768 dimensions
+- **Similarity Function:** Cosine Similarity
+
+### Full Model Architecture
+
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: ModernBertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
+)
+```
+
+## 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("sentence_transformers_model_id")
+# Run inference
+sentences = [
+    'الذكاء الاصطناعي يغير طريقة تفاعلنا مع التكنولوجيا.',
+    'التكنولوجيا تتطور بسرعة بفضل الذكاء الاصطناعي.',
+    'الذكاء الاصطناعي يسهم في تطوير التطبيقات الذكية.',
+]
+embeddings = model.encode(sentences)
+print(embeddings.shape)
+# [3, 768]
+
+# Get the similarity scores for the embeddings
+similarities = model.similarity(embeddings, embeddings)
+print(similarities.shape)
+# [3, 3]
+```
+
+## Evaluation
+
+### Metrics
+
+#### Semantic Similarity
+
+* Datasets: ` STS17` and `STS22.v2`
+* Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator)
+
+| Metric              | STS17     | STS22.v2   |
+|:--------------------|:----------|:-----------|
+| pearson_cosine      | 0.8249    | 0.5259     |
+| **spearman_cosine** | **0.831** | **0.6169** |
+
+<!--
+## 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.*
+-->
+
+### Framework Versions
+- Python: 3.10.12
+- Sentence Transformers: 3.4.1
+- Transformers: 4.49.0
+- PyTorch: 2.1.0+cu118
+- Accelerate: 1.4.0
+- Datasets: 2.21.0
+- Tokenizers: 0.21.0
+
+## 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",
+}
+```
+
+#### MultipleNegativesRankingLoss
+```bibtex
+@misc{henderson2017efficient,
+    title={Efficient Natural Language Response Suggestion for Smart Reply},
+    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
+    year={2017},
+    eprint={1705.00652},
+    archivePrefix={arXiv},
+    primaryClass={cs.CL}
+}
+```

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "NAMAA-Space/AraModernBert-Base-V1.0",
+  "additional_special_tokens_ids": [],
+  "architectures": [
+    "ModernBertModel"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 3,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": null,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "mask_token_id": 6,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 5,
+  "position_embedding_type": "absolute",
+  "reference_compile": false,
+  "repad_logits_with_grad": false,
+  "sep_token_id": 4,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "unk_token_id": 2,
+  "vocab_size": 50280
+}

config_sentence_transformers.json

@@ -0,0 +1,10 @@
+{
+  "__version__": {
+    "sentence_transformers": "3.4.1",
+    "transformers": "4.49.0",
+    "pytorch": "2.1.0+cu118"
+  },
+  "prompts": {},
+  "default_prompt_name": null,
+  "similarity_fn_name": "cosine"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a840401f05761949351c98fd7d02602b0684be881786711e14591238e60bd4dd
+size 595799800

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

sentence_bert_config.json

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

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "[UNK]"
+}