Upload 9 files

.gitattributes

@@ -33,3 +33,5 @@ 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
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,97 @@
 ---
-license: cc-by-nc-4.0
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-ar-en
+tags:
+- machine-translation
+- marian
+- mcwc
+- legal-nlp
+- constitutional-texts
+- generated_from_keras_callback
+model-index:
+- name: marian-finetuned-mcwc-ara-to-en
+  results: []
 ---
+
+# Marian MT fine-tuned on the Multilingual Corpus of World’s Constitutions (MCWC)
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-es-en](https://huggingface.co/Helsinki-NLP/opus-mt-es-en), adapted using high-quality sentence-aligned constitutional text from the **Multilingual Corpus of World’s Constitutions (MCWC)**  
+📄 MCWC paper (OSACT 2024): https://aclanthology.org/2024.osact-1.7/
+
+**This variant handles: _Arabic → English_ translation.**
+
+---
+
+## Overview
+The MCWC provides a curated multilingual collection of constitutional texts from countries across the world. The corpus emphasises data cleanliness, high-quality sentence alignment, and detailed metadata (including country and continent mappings). It supports research in:
+
+- legal and constitutional NLP  
+- comparative constitutional studies  
+- multilingual machine translation  
+- cross-lingual semantic analysis  
+
+This model was fine-tuned on the Arabic-English segment of the MCWC, enabling translation that is more attuned to legal and constitutional language than general-purpose MT systems.
+
+---
+
+## Intended use
+This model is suitable for tasks such as:
+
+- translating constitutional or legal documents  
+- cross-lingual legal text comparison  
+- multilingual information extraction  
+- downstream legal NLP tasks requiring domain-specific MT  
+
+It is **not** intended for casual or conversational translation, as it is optimised for formal and legal text.
+
+---
+
+## Training data
+The model was trained on the MCWC’s Arabic-English aligned sentence pairs.  
+The MCWC dataset includes:
+
+- cleaned constitutional text  
+- high-quality sentence segmentation  
+- pairwise alignments  
+- country and regional metadata  
+
+More details may be found in the accompanying paper:
+> *El-Haj, M. & Ezzini, S. (2024). “The Multilingual Corpus of World’s Constitutions (MCWC).”*  
+> OSACT @ LREC-COLING 2024.  
+> https://aclanthology.org/2024.osact-1.7/
+
+---
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 384, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- training_precision: mixed_float16
+
+### Training results
+
+| Train Loss | Validation Loss | Epoch |
+|:----------:|:---------------:|:-----:|
+| 1.3918     | 1.1473          | 0     |
+| 1.0745     | 1.1021          | 1     |
+| 0.9486     | 1.0908          | 2     |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- TensorFlow 2.13.0
+- Datasets 2.14.5
+- Tokenizers 0.13.3
+
+---
+
+## Citation
+
+If you use this model, please cite the MCWC paper:
+
+**El-Haj, M. & Ezzini, S. (2024).**  
+*The Multilingual Corpus of World’s Constitutions (MCWC).*  
+Proceedings of OSACT @ LREC-COLING 2024.  
+https://aclanthology.org/2024.osact-1.7/

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-ar-en",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      62833
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 62833,
+  "decoder_vocab_size": 62834,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 62833,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 62834
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      62833
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 62833,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 62833,
+  "transformers_version": "4.33.3"
+}

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484f7210e5f4466f7e5b99b660717c6ef2a6f90746196daba507795b69dc02a2
+size 917407

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156cae4f035ba812224e79d71626802a07296a3ad2ea5c6bc1f2cb35420dfeb4
+size 801886

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4adec1e6a5da2ac097d51bc7bed3d2e207bf1ee4ae453c4afc3facf40419a718
+size 307873912

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "return_tensors": "pt",
+  "separate_vocabs": false,
+  "source_lang": "ar",
+  "sp_model_kwargs": {},
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}