Upload folder using huggingface_hub

README.md

@@ -0,0 +1,27 @@
+
+# StrongTextCNN
+
+A CNN-based text classification model trained using PyTorch.
+
+## Model Architecture
+
+- Embedding Layer (300 dimensions)
+- Conv1D kernels: 2, 3, 4, 5
+- 128 filters each
+- Batch Normalization
+- Fully Connected Layers:
+  - 512 → 256
+  - 256 → 64
+  - 64 → 1
+- Dropout = 0.4
+
+## Files
+
+- model.py
+- best_model.pt
+- tokenizer/
+
+## Usage
+
+```python
+from model import StrongTextCNN

best_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9acaade9422b45680fc6d30d38ed35fe8937b0661f75ba1320e00c104b7288b4
+size 39385653

model.py

@@ -0,0 +1,68 @@
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+class StrongTextCNN(nn.Module):
+
+    def __init__(
+        self,
+        vocab_size,
+        embed_dim=300,
+        num_filters=128,
+        dropout=0.4
+    ):
+        super().__init__()
+
+        self.embedding = nn.Embedding(
+            vocab_size,
+            embed_dim,
+            padding_idx=0
+        )
+
+        self.convs = nn.ModuleList([
+            nn.Conv1d(embed_dim, num_filters, k)
+            for k in [2,3,4,5]
+        ])
+
+        self.bn = nn.BatchNorm1d(num_filters * 4)
+
+        self.fc1 = nn.Linear(num_filters * 4, 256)
+        self.fc2 = nn.Linear(256, 64)
+        self.out = nn.Linear(64, 1)
+
+        self.dropout = nn.Dropout(dropout)
+
+    def forward(self, x):
+
+        x = self.embedding(x)
+        x = x.permute(0,2,1)
+
+        conv_outputs = []
+
+        for conv in self.convs:
+
+            c = F.relu(conv(x))
+
+            p = F.max_pool1d(
+                c,
+                kernel_size=c.shape[2]
+            ).squeeze(2)
+
+            conv_outputs.append(p)
+
+        x = torch.cat(conv_outputs, dim=1)
+
+        x = self.bn(x)
+
+        x = self.dropout(x)
+
+        x = F.relu(self.fc1(x))
+        x = self.dropout(x)
+
+        x = F.relu(self.fc2(x))
+        x = self.dropout(x)
+
+        x = self.out(x)
+
+        return x.squeeze(1)

requirements.txt

@@ -0,0 +1,3 @@
+torch
+transformers
+tokenizers

tokenizer/tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}