Sync model from GitHub repository

Automated sync via GitHub Action / script

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -48,6 +48,17 @@ widget:
 
 # CompactNameClassifier: Ultra-Efficient Name Classifier Trained From Scratch
 
+<div align="center">
+
+[![Hugging Face](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model%20Hub-yellow.svg)](https://huggingface.co/SupratimRK/compact-name-classifier)
+[![GitHub](https://img.shields.io/badge/GitHub-Repository-black?logo=github)](https://github.com/SupratimRK/compact-name-classifier)
+[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
+[![ONNX Runtime](https://img.shields.io/badge/ONNX-INT8%20Quantized-blue)](https://onnxruntime.ai/)
+
+**[🤗 Hugging Face Model Hub](https://huggingface.co/SupratimRK/compact-name-classifier)** | **[🐙 GitHub Repository](https://github.com/SupratimRK/compact-name-classifier)**
+
+</div>
+
 `CompactNameClassifier` is a state-of-the-art, ultra-lightweight neural text classifier trained **from scratch** on a curated dataset of **455,669 records** (245.7k real human names across global cultures + 210.0k non-names, usernames, gamer tags, and alphanumeric codes).
 
 Unlike generic large language models or pretrained BERT variants, `CompactNameClassifier` has **zero external pretrained dependencies**, weighs just **~647 KB** (INT8 ONNX), and delivers sub-millisecond CPU inference (**< 0.25 ms per query**).
@@ -164,28 +175,22 @@ CSE3048              => NON_NAME (99.9%)
 
 ---
 
-### 3. Node.js Inference (onnxruntime-node)
+### 3. Node.js Native Inference (onnxruntime-node)
 
 ```javascript
-import ort from 'onnxruntime-node';
-
-// Set single-thread session for sub-millisecond execution
-const sessionOpts = {
-  intraOpNumThreads: 1,
-  interOpNumThreads: 1
-};
-const session = await ort.InferenceSession.create('./model_int8.onnx', sessionOpts);
-
-const inputIds = new Int32Array(20); // padded token ids
-const attentionMask = new Int32Array(20); // 1 for tokens, 0 for pad
-
-const feeds = {
-  input_ids: new ort.Tensor('int32', inputIds, [1, 20]),
-  attention_mask: new ort.Tensor('int32', attentionMask, [1, 20])
-};
-
-const results = await session.run(feeds);
-console.log(results);
+import { CompactNameClassifier } from './scripts/classifier.mjs';
+
+const classifier = new CompactNameClassifier();
+await classifier.init();
+
+const result = await classifier.predict('Sayantika Biswas');
+console.log(result);
+// {
+//   text: 'Sayantika Biswas',
+//   classification: 'REAL_NAME',
+//   confidence: 0.998,
+//   raw_probs: { non_name: 0.002, real_name: 0.998 }
+// }
 ```
 
 ---
@@ -194,7 +199,7 @@ console.log(results);
 
 ```python
 import torch
-from model import CompactNameClassifier
+from scripts.model import CompactNameClassifier
 
 model = CompactNameClassifier(
     vocab_size=4000,
@@ -205,7 +210,7 @@ model = CompactNameClassifier(
     max_len=20,
     dropout=0.0
 )
-model.load_state_dict(torch.load("model_weights.pt", weights_only=True))
+model.load_state_dict(torch.load("models/model_weights.pt", weights_only=True))
 model.eval()
 ```
 

config.json

@@ -1,26 +1,26 @@
-{
-  "model_type": "CompactNameClassifier",
-  "architectures": [
-    "CompactNameClassifier"
-  ],
-  "vocab_size": 4000,
-  "emb_dim": 64,
-  "hidden_dim": 128,
-  "num_layers": 2,
-  "num_heads": 4,
-  "dim_feedforward": 256,
-  "max_length": 20,
-  "dropout": 0.1,
-  "id2label": {
-    "0": "NON_NAME",
-    "1": "REAL_NAME"
-  },
-  "label2id": {
-    "NON_NAME": 0,
-    "REAL_NAME": 1
-  },
-  "metrics": {
-    "best_val_accuracy": 0.9547553093259464,
-    "best_val_f1": 0.9586647384912027
-  }
-}
+{
+  "model_type": "CompactNameClassifier",
+  "architectures": [
+    "CompactNameClassifier"
+  ],
+  "vocab_size": 4000,
+  "emb_dim": 64,
+  "hidden_dim": 128,
+  "num_layers": 2,
+  "num_heads": 4,
+  "dim_feedforward": 256,
+  "max_length": 20,
+  "dropout": 0.1,
+  "id2label": {
+    "0": "NON_NAME",
+    "1": "REAL_NAME"
+  },
+  "label2id": {
+    "NON_NAME": 0,
+    "REAL_NAME": 1
+  },
+  "metrics": {
+    "best_val_accuracy": 0.9547553093259464,
+    "best_val_f1": 0.9586647384912027
+  }
+}

predict.py

@@ -10,20 +10,12 @@ sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
 from model import CompactNameClassifier
 
 SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
-if os.path.exists(os.path.join(SCRIPT_DIR, "config.json")):
-    PROJECT_ROOT = SCRIPT_DIR
-    MODELS_DIR = SCRIPT_DIR
-    CONFIG_PATH = os.path.join(SCRIPT_DIR, "config.json")
-    TOKENIZER_DIR = SCRIPT_DIR
-    ONNX_PATH = os.path.join(SCRIPT_DIR, "model_int8.onnx")
-    WEIGHTS_PATH = os.path.join(SCRIPT_DIR, "model_weights.pt")
-else:
-    PROJECT_ROOT = os.path.abspath(os.path.join(SCRIPT_DIR, ".."))
-    MODELS_DIR = os.path.join(PROJECT_ROOT, "models")
-    CONFIG_PATH = os.path.join(PROJECT_ROOT, "config", "model_config.json")
-    TOKENIZER_DIR = os.path.join(MODELS_DIR, "tokenizer")
-    ONNX_PATH = os.path.join(MODELS_DIR, "model_int8.onnx")
-    WEIGHTS_PATH = os.path.join(MODELS_DIR, "model_weights.pt")
+PROJECT_ROOT = os.path.abspath(os.path.join(SCRIPT_DIR, ".."))
+MODELS_DIR = os.path.join(PROJECT_ROOT, "models")
+CONFIG_PATH = os.path.join(PROJECT_ROOT, "config", "model_config.json")
+TOKENIZER_DIR = os.path.join(MODELS_DIR, "tokenizer")
+ONNX_PATH = os.path.join(MODELS_DIR, "model_int8.onnx")
+WEIGHTS_PATH = os.path.join(MODELS_DIR, "model_weights.pt")
 
 class NameClassifier:
     """