add files

app.py

@@ -0,0 +1,68 @@
+# -*- coding: utf-8 -*-
+"""Untitled31.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1qkQ5UtvWMcQKdxpkEgZhStoBplz9kcAo
+"""
+
+
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, Trainer, TrainingArguments
+from datasets import Dataset
+import gradio as gr
+import torch
+
+data = {
+    "text": [
+        "Proficient in Python and Machine Learning",
+        "Excellent written and verbal communication",
+        "Experience with cloud platforms like AWS and Azure",
+        "Skilled in data visualization and analytics",
+        "Project management and Agile methodologies"
+    ],
+    "label": [0, 1, 0, 0, 1]  # 0 = Technical, 1 = Soft Skill
+}
+
+dataset = Dataset.from_dict(data)
+
+model_checkpoint = "distilbert-base-uncased"
+tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
+
+def tokenize(batch):
+    return tokenizer(batch["text"], padding=True, truncation=True)
+
+tokenized_dataset = dataset.map(tokenize, batched=True)
+
+model = AutoModelForSequenceClassification.from_pretrained(model_checkpoint, num_labels=2)
+
+training_args = TrainingArguments(
+    output_dir="./results",
+    evaluation_strategy="no",
+    per_device_train_batch_size=2,
+    num_train_epochs=3,
+    logging_steps=10,
+    push_to_hub=False,
+    report_to="none"
+)
+
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_dataset
+)
+
+trainer.train()
+
+def classify(text):
+    inputs = tokenizer(text, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model(**inputs)
+    prediction = torch.argmax(outputs.logits, dim=1).item()
+    return "Soft Skill" if prediction == 1 else "Technical Skill"
+
+print(classify("Familiar with cloud computing and Docker"))
+
+interface = gr.Interface(fn=classify, inputs="text", outputs="text")
+interface.launch()
+

requirements.txt

@@ -0,0 +1,4 @@
+datasets
+gradio
+torch
+transformers