🚀 Deploy Hugging Face Gradio version with updated README

.gitignore

@@ -0,0 +1,21 @@
+# Python virtual environment
+venv/
+__pycache__/
+*.pyc
+
+# VSCode & OS junk
+.vscode/
+.DS_Store
+
+# Environment files
+.env
+.env.*
+
+# Model folders (only ignore unnecessary subfolders)
+model/__results__files/
+model/results.zip
+model/sentiment_model/
+model/*__huggingface_repo__*
+
+# Don't ignore actual model files that are used!
+# Keep: model.safetensors, tokenizer.json, config.json, etc.

README.md

@@ -0,0 +1,51 @@
+# 🧠 Sentiment Analysis V2 (Gradio Version)
+
+A lightweight sentiment classification web app using a fine-tuned **BERT** model.
+
+> Hosted entirely on [🤗 Hugging Face Spaces](https://huggingface.co/spaces/McKlay/SentimentAnalysisV2-HF) using **Gradio** and **Transformers**.
+
+---
+
+## ⚙️ Tech Stack
+- 🤗 **Transformers** for BERT-based text classification
+- 🔥 **PyTorch** for model inference
+- 🎨 **Gradio** for building the web interface
+- 🚀 **Hugging Face Spaces** for free app hosting
+
+---
+
+## 🧪 Try It Out
+Paste a sentence into the textbox and get real-time sentiment probabilities (positive/negative) with confidence levels.
+
+---
+
+## 📁 File Structure
+SentimentAnalysisV2-HF/ 
+├── app.py # Main Gradio app 
+├── model/ # empty, the model is located in model hub McKlay/sentiment-analysis-v2 
+├── requirements.txt # Dependency file 
+├── .gitignore └── README.md
+
+---
+
+## ✅ How It Works
+
+1. Loads the tokenizer and model from the `model/` folder.
+2. Processes input text and runs inference using BERT.
+3. Returns the confidence scores for each sentiment label.
+4. All of this happens **live** in your browser via Gradio!
+
+---
+
+## ✨ Author
+
+**Clay Mark Sarte**  
+[GitHub: @McKlay](https://github.com/McKlay)  
+Passionate about AI, ML, and building useful tools with minimal stack.
+
+---
+
+## 📜 License
+
+MIT License — free to use and modify.
+

app.py

@@ -0,0 +1,26 @@
+import gradio as gr
+from transformers import BertTokenizer, BertForSequenceClassification
+import torch
+
+# Load model and tokenizer from Hugging Face Hub
+MODEL_DIR = "McKlay/sentiment-analysis-v2"
+tokenizer = BertTokenizer.from_pretrained(MODEL_DIR)
+model = BertForSequenceClassification.from_pretrained(MODEL_DIR)
+model.eval()
+
+# Define prediction function
+def analyze_sentiment(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+    outputs = model(**inputs)
+    probs = torch.nn.functional.softmax(outputs.logits, dim=1)
+    labels = ['Negative', 'Positive']
+    return {labels[i]: float(probs[0][i]) for i in range(2)}
+
+# Launch Gradio interface
+gr.Interface(
+    fn=analyze_sentiment,
+    inputs=gr.Textbox(lines=3, placeholder="Enter a comment..."),
+    outputs=gr.Label(num_top_classes=2),
+    title="Sentiment Analysis V2 (Gradio)",
+    description="Real-time sentiment analysis using a BERT-based model. Powered by 🤗 Transformers and Gradio."
+).launch()

requirements.txt

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