Upload folder using huggingface_hub

README.md

@@ -1,3 +1,59 @@
----
-license: mit
----
+---
+language: multilingual
+license: mit
+tags:
+  - transformer
+  - summarization
+  - translation
+  - question-answering
+  - english
+  - arabic
+---
+
+# Miscovery Transformer Model
+
+This model is a transformer-based encoder-decoder model for multiple NLP tasks:
+- Text summarization
+- Translation (English-Arabic)
+- Question-answering
+
+## Model Architecture
+
+- Model type: miscovery
+- Number of parameters: 485674144
+- Encoder layers: 12
+- Decoder layers: 12
+- Attention heads: 12
+- Hidden size: 768
+- Feed-forward size: 3072
+
+## Training
+
+The model was trained in two stages:
+1. Pre-training on sentence rearrangement tasks
+2. Fine-tuning on downstream tasks
+
+## Usage
+
+1. Install the package:
+
+```bash
+pip install miscovery_model
+```
+
+2. Run the model using a script:
+
+```python
+from miscovery_model import standard_pipeline
+
+# Create a pipeline
+model = standard_pipeline("miscovery/model")
+
+# Use it
+result = model("Translate this to Arabic: What year did World War I begin?")
+print(result)
+```
+
+## Limitations
+
+This model was trained on specific datasets and may not generalize well to all domains.

__init__.py

@@ -0,0 +1,9 @@
+"""Miscovery model package."""
+
+from .configuration_miscovery import CustomTransformerConfig
+from .modeling_miscovery import CustomTransformerModel
+
+__all__ = [
+    "CustomTransformerConfig",
+    "CustomTransformerModel",
+]

config.json

@@ -0,0 +1,20 @@
+{
+  "architectures": [
+    "CustomTransformerModel"
+  ],
+  "bos_token_id": 2,
+  "d_ff": 3072,
+  "d_model": 768,
+  "dropout": 0.1,
+  "eos_token_id": 3,
+  "max_position_embeddings": 512,
+  "model_type": "miscovery",
+  "num_decoder_layers": 12,
+  "num_encoder_layers": 12,
+  "num_heads": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_flash_attn": true,
+  "vocab_size": 100000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

special_tokens_map.json

@@ -0,0 +1,42 @@
+{
+  "additional_special_tokens": [
+    "[LANG_EN]",
+    "[LANG_AR]",
+    "[LANG_AR_EG]"
+  ],
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "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 +1,82 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "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
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[LANG_EN]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[LANG_AR]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "[LANG_AR_EG]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "[LANG_EN]",
+    "[LANG_AR]",
+    "[LANG_AR_EG]"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": "[UNK]"
+}