Upload trained Ibani translation model

.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

@@ -0,0 +1,67 @@
+---
+language:
+- en
+- iba
+license: apache-2.0
+tags:
+- translation
+- ibani
+- english-to-ibani
+- low-resource
+library_name: transformers
+pipeline_tag: translation
+---
+
+# English to Ibani Translation Model
+
+This model translates English text to Ibani language. It's fine-tuned from Helsinki-NLP/opus-mt-en-mul.
+
+## Usage
+
+```python
+from transformers import MarianMTModel, MarianTokenizer
+
+model = MarianMTModel.from_pretrained("your-username/ibani-translator")
+tokenizer = MarianTokenizer.from_pretrained("your-username/ibani-translator")
+
+text = "I eat fish"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model.generate(**inputs)
+translation = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(translation)
+```
+
+## Training Data
+
+Trained on English-Ibani parallel sentences from the ibani_eng dataset.
+
+## Performance
+
+[Add your evaluation metrics here]
+
+## Model Details
+
+- **Base Model**: Helsinki-NLP/opus-mt-en-mul
+- **Language Pair**: English → Ibani
+- **Task**: Machine Translation
+- **Framework**: Hugging Face Transformers
+
+## Limitations
+
+- This is a low-resource language model
+- Performance may vary with complex sentence structures
+- Best results with simple to moderate complexity sentences
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{ibani-translator,
+  author = {Your Name},
+  title = {English to Ibani Translation Model},
+  year = {2025},
+  publisher = {Hugging Face},
+  howpublished = {\url{https://huggingface.co/your-username/ibani-translator}}
+}
+```

config.json

@@ -0,0 +1,54 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 64109,
+  "decoder_vocab_size": 64110,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 64110,
+  "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": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 64109,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "vocab_size": 64110
+}

generation_config.json

@@ -0,0 +1,17 @@
+{
+  "bad_words_ids": [
+    [
+      64109
+    ]
+  ],
+  "decoder_start_token_id": 64109,
+  "eos_token_id": [
+    0
+  ],
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 64109,
+  "renormalize_logits": true,
+  "transformers_version": "4.56.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2ce0d525787165c8daedbcc01bd1d68e96cfc10f32a94775d8cd5fffd84d69c
+size 308136760

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9129bf81ef9d5fcc1797ea3061e789dc5f9e5602786b0490238d207d4219e0f5
+size 790473

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 sha256:6a0a52318dac3247455ec889eb3bd8da9bdf234974be8b9b0f99ad5378f474c9
+size 706659

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64109": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "eng",
+  "sp_model_kwargs": {},
+  "target_lang": "mul",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50a0dac07f865b2800ec9c9ad89f26dad78a3af95aa380bcd609a558ec1dc08d
+size 5905