Upload folder using huggingface_hub

.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 +1,99 @@
+
+# Swahili-English Translation Model (General Domain Expansion)
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-mul-en](https://huggingface.co/Helsinki-NLP/opus-mt-mul-en) 
+on a large corpus of general Swahili-English translations while maintaining helpline translation quality.
+
+## Model Details
+
+- **Base Model:** Helsinki-NLP/opus-mt-mul-en
+- **Language Pair:** Swahili (sw) → English (en)
+- **Training Data:** 
+  - CCAligned general corpus (~200k+ samples)
+  - Helpline conversation data (oversampled 5x for domain retention)
+- **Special Features:**
+  - Domain-aware with `<HELPLINE>` and `<GENERAL>` tags
+  - Optimized for both general and helpline translations
+  - Knowledge distillation from helpline-specialized model
+
+## Training Procedure
+
+### Memory Optimizations
+- CPU teacher offloading
+- Gradient checkpointing
+- Batch size: 8, Gradient accumulation: 16
+
+### Training Hyperparameters
+- Learning rate: 1.5e-5
+- Epochs: 1
+- Optimizer: AdamW
+- LR Scheduler: Cosine with warmup
+
+## Performance
+
+| Domain | BLEU | chrF |
+|--------|------|------|
+| Helpline | X.XX | XX.X |
+| General | X.XX | XX.X |
+
+*(Replace with actual metrics from training)*
+
+## Usage
+
+```python
+from transformers import MarianMTModel, MarianTokenizer
+
+# Load model and tokenizer
+model_name = "brendaogutu/sw-en-opus-mt-general-expanded"
+tokenizer = MarianTokenizer.from_pretrained(model_name)
+model = MarianMTModel.from_pretrained(model_name)
+
+# For general translations
+text = "<GENERAL> Habari za asubuhi"
+inputs = tokenizer(text, return_tensors="pt", padding=True)
+outputs = model.generate(**inputs)
+translation = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(translation)  # "Good morning"
+
+# For helpline translations
+text = "<HELPLINE> Ninahitaji msaada wa haraka"
+inputs = tokenizer(text, return_tensors="pt", padding=True)
+outputs = model.generate(**inputs)
+translation = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(translation)  # "I need urgent help"
+```
+
+## Limitations
+
+- Optimized for Swahili to English (not bidirectional)
+- Best performance with domain tags (<HELPLINE> or <GENERAL>)
+- May struggle with very technical or specialized vocabulary outside training domains
+
+## Training Details
+
+- **Framework:** Transformers + PyTorch
+- **Hardware:** Single GPU training
+- **Training Time:** ~X hours
+- **Checkpoint Strategy:** Every 500 steps for power failure recovery
+
+## Citation
+
+If you use this model, please cite:
+
+```bibtex
+@misc{{sw-en-general-expanded,
+  author = {{Your Name/Organization}},
+  title = {{Swahili-English General Domain Translation Model}},
+  year = {{2025}},
+  publisher = {{HuggingFace}},
+  url = {{https://huggingface.co/brendaogutu/sw-en-opus-mt-general-expanded}}
+}}
+```
+
+## License
+
+This model inherits the license from Helsinki-NLP/opus-mt-mul-en.
+
+## Contact
+
+For questions or issues, please open an issue on the model repository.

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<GENERAL>": 64173,
+  "<HELPLINE>": 64172
+}

config.json

@@ -0,0 +1,55 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 64171,
+  "decoder_vocab_size": 64174,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 64172,
+  "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": 64171,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.2",
+  "use_cache": true,
+  "vocab_size": 64174
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      64171
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 64171,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 64171,
+  "renormalize_logits": true,
+  "transformers_version": "4.53.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6550b6e094e8afaf9f13fa30563127f02078159809b15dc0ae1792d436177834
+size 308268088

register_to_mlflow.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+python register_model.py \
+  --model_path /home/brenda/chl_scratch/openchs_rnd/tasks/translation/swahili/models/finetuned-sw-en-general-v2 \
+  --experiment_name translation-sw-en \
+  --model_name opus-mt-sw-en-general-expanded-v2 \
+  --run_id 789785bf2e554d8b8aec869cc9648edc \
+  --mlflow_uri http://localhost:5000

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a99ea3602b29fbf901ade8b93a45efa3d7c64eab8fc5fa812383efa327a87d
+size 706917

special_tokens_map.json

@@ -0,0 +1,46 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<HELPLINE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<GENERAL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<GENERAL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6dce5fa58fcd7dde9e81e279b8c075bf42ee558278f73d6fb48e342029d7f19
+size 791194

tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "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
+    },
+    "64171": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64172": {
+      "content": "<HELPLINE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "64173": {
+      "content": "<GENERAL>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<HELPLINE>",
+    "<GENERAL>",
+    "<GENERAL>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "mul",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

training_metadata.json

@@ -0,0 +1,17 @@
+{
+  "baseline_helpline_bleu": 0.7138171930464564,
+  "baseline_general_bleu": 0.08336173164014311,
+  "final_helpline_bleu": 0.7017193706052336,
+  "final_general_bleu": 0.14619497807657425,
+  "helpline_retention": 0.983051931840432,
+  "general_improvement": 1.7537420972451774,
+  "production_ready": true,
+  "training_samples": 256146,
+  "validation_samples": 5228,
+  "model_info": {
+    "model_name": "openchs/sw-en-opus-mt-mul-en-v1",
+    "total_parameters": 77519872,
+    "trainable_parameters": 76995584,
+    "vocab_size": 64174
+  }
+}