Add application file

app.py

@@ -0,0 +1,52 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+import contractions
+import html
+import re
+
+# Load model and tokenizer
+model_path = "my_model"  # directory with your trained model
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModelForSequenceClassification.from_pretrained(model_path)
+
+# Labels
+id2label = {
+    0: 'Anxiety',
+    1: 'BPD',
+    2: 'Normal',
+    3: 'bipolar',
+    4: 'depression',
+    5: 'mentalillness',
+    6: 'schizophrenia'
+}
+
+# Inference function
+def predict(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    pred_id = outputs.logits.argmax(dim=1).item()
+    return id2label[pred_id]
+
+def clean_text(text):
+    text = str(text)
+    text = text.lower()
+    text = contractions.fix(text)
+    text = html.unescape(text)
+    text = re.sub(r'http\S+', '', text)  # Remove URLs
+    text = re.sub(r'[^a-zA-Z\s]', '', text)  # Remove special characters
+    text = re.sub(r'\s+', ' ', text).strip()
+    return text
+
+# Gradio UI
+demo = gr.Interface(
+    fn=predict,
+    inputs=gr.Textbox(lines=3, placeholder="Enter text here..."),
+    outputs=gr.Label(),
+    title="Mental Health Text Classifier",
+    description="Predicts mental health category based on text input."
+)
+
+if __name__ == "__main__":
+    demo.launch()

my_model/config.json

@@ -0,0 +1,42 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "vocab_size": 30522
+}

my_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a4924aae12999707576d94fab86410a96602f4ad8e7b2c267f6b2eda9ac89a
+size 267847948

my_model/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

my_model/tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

requirements.txt

@@ -0,0 +1,6 @@
+transformers
+torch
+gradio
+contractions
+html
+re