Update model card: add ONNX runtime guide and application use cases

README.md

@@ -10,13 +10,15 @@ tags:
 - roberta
 - sentencepiece
 - custom-code
+- onnx
+- onnxruntime
 ---
 
 # BashkirRoBERTa
 
 A masked language model for Bashkir. Given a sentence with one `[MASK]` token,
 it predicts the most probable missing Bashkir token from its context. The model
-is useful for fill-mask experiments and as a starting point for further
+is useful for fill-mask experiments, spellchecking, and as a foundation for further
 fine-tuning.
 
 ## Examples
@@ -28,7 +30,7 @@ fine-tuning.
 | `Өфө — ҙур [MASK].` | `ҡала` |
 | `Бөгөн Өфөлә яңы [MASK] асылды.` | `мәктәп` |
 
-## Model
+## Model Architecture
 
 | Property | Value |
 | --- | --- |
@@ -56,7 +58,7 @@ accuracy for masked subword prediction.
 These are diagnostic MLM results, not a general-purpose language-understanding
 score. A mask may represent a whole word or a SentencePiece subword fragment.
 
-## Loading
+## PyTorch Loading (Transformers)
 
 ```python
 from transformers import AutoModelForMaskedLM, AutoTokenizer
@@ -76,6 +78,44 @@ print(tokenizer.decode([prediction_id]))  # яратам
 Pre-LayerNorm architecture rather than using the stock post-LayerNorm RoBERTa
 implementation.
 
+## ⚡ ONNX Runtime (Fast CPU & Edge Deployment)
+
+For resource-constrained devices, edge environments, and production without heavy PyTorch dependencies,
+pre-compiled ONNX models are available in the `onnx/` folder:
+
+- **`onnx/model_fp16.onnx`** (95.4 MB): Recommended for GPU and DirectML acceleration.
+- **`onnx/model_int8.onnx`** (58.1 MB): Quantized INT8 checkpoint for ultra-fast CPU, server, and mobile (Android/iOS) inference with negligible accuracy difference.
+
+```python
+import numpy as np
+import onnxruntime as ort
+import sentencepiece as spm
+from huggingface_hub import hf_hub_download
+
+# Download lightweight INT8 model and tokenizer (~58 MB total)
+model_path = hf_hub_download("failed09/bashkir-roberta", "onnx/model_int8.onnx")
+sp_path = hf_hub_download("failed09/bashkir-roberta", "spm_bashkir_bert_16k.model")
+
+session = ort.InferenceSession(model_path, providers=["CPUExecutionProvider"])
+sp = spm.SentencePieceProcessor(model_file=sp_path)
+
+# Tokenize sentence with [MASK]
+tokens = [2] + sp.encode("Мин башҡорт телен ") + [6] + sp.encode(".") + [3]
+mask_idx = tokens.index(6)
+inputs = {"input_ids": np.array([tokens], dtype=np.int64)}
+
+logits = session.run(None, inputs)[0][0, mask_idx]
+top_tokens = np.argsort(logits)[::-1][:5]
+print([sp.decode([int(t)]) for t in top_tokens])  # ['яратам', 'беләм', 'өйрәнә', ...]
+```
+
+## 🎯 Target Applications
+
+- **Grammar & Spellchecking:** Contextual candidate ranking, detection of morphological errors and vowel harmony violations.
+- **Cloze & Multiple-Choice Testing:** Automated solving and candidate evaluation for Bashkir educational tests.
+- **OCR Post-Correction:** Resolving noisy characters and ambiguous glyphs in digitized historical print.
+- **Feature Extraction & Fine-Tuning:** Backbone representations for Bashkir text classification, sentiment analysis, and NER.
+
 ## License and provenance
 
 The checkpoint is released under custom terms (`other` on the Hub) while the