initial commit

.gitattributes copy

@@ -0,0 +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

Dockerfile

@@ -0,0 +1,24 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Create a non-root user and switch to it
+RUN useradd -m -u 1000 user
+USER user
+
+# Set environment variables
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH \
+    HF_HOME=/home/user/.cache/huggingface/transformers
+
+WORKDIR $HOME/app
+
+# Ensure the user owns the copied files
+COPY --chown=user . $HOME/app
+
+# Command to run the application with Uvicorn
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,47 @@
+
+import torch 
+from fastapi import FastAPI, Request
+from fastapi.responses import HTMLResponse
+from fastapi.staticfiles import StaticFiles
+from starlette.responses import FileResponse
+
+from transformers import AutoModelForSequenceClassification, AutoTokenizer, pipeline
+import torch.nn.functional as F
+
+app = FastAPI()
+
+model_name = "distilbert-base-uncased-finetuned-sst-2-english"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+
+app.mount("/static", StaticFiles(directory="static", html=True), name="static")
+
+@app.get("/", response_class=HTMLResponse)
+async def read_index():
+    return FileResponse("static/index.html")
+
+@app.get("/classify_text")
+async def classify_text(input: str):
+    inputs = tokenizer(input, return_tensors="pt")
+    outputs = model(**inputs)
+    
+    # Convert logits to probabilities
+    probabilities = F.softmax(outputs.logits, dim=-1)
+
+    # Assuming we're using a binary classification model here (positive, negative)
+    # Adjust indices [0, 1] based on your model's specific output mapping
+    positive_prob = probabilities[:, 1].item()  # Probability of positive sentiment
+    negative_prob = probabilities[:, 0].item()  # Probability of negative sentiment
+
+    # You can also use `torch.argmax` to just return the most likely class
+    sentiment = "positive" if torch.argmax(probabilities) == 1 else "negative"
+
+    return {
+        "input": input,
+        "positive_probability": positive_prob,
+        "negative_probability": negative_prob,
+        "sentiment": sentiment,
+    }
+
+
+# uvicorn main:app --host 127.0.0.1 --port 8001 --reload

requirements.txt

@@ -0,0 +1,7 @@
+fastapi==0.74.*
+requests==2.27.*
+sentencepiece==0.1.*
+torch==1.11.*
+transformers==4.*
+uvicorn[standard]==0.17.*
+

static/index.html

@@ -0,0 +1,36 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Text Classification Form</title>
+</head>
+<body>
+<main>
+    <section id="text-class">
+      <h2>Text classification using distilbert-base-uncased</h2>
+      <p>
+        Model:
+        <a
+          href="https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english"
+          rel="noreferrer"
+          target="_blank">distilbert-base-uncased
+        </a>
+      </p>
+      <form class="text-class-form" id="textClassForm">
+        <label for="text-class-input">Text prompt:</label>
+        <input
+          id="text-class-input"
+          name="text"
+          type="text"
+          placeholder="I am feeling lucky today"
+        />
+        <button type="submit" id="text-class-submit">Submit</button>
+      </form>
+      <p class="text-class-output"></p>
+    </section>
+  </main>
+
+<script src="static/script.js"></script>
+</body>
+</html>

static/script.js

@@ -0,0 +1,35 @@
+document.addEventListener("DOMContentLoaded", () => {
+    const textClassForm = document.querySelector(".text-class-form");
+  
+    const classifyText = async (text) => {
+        try {
+            // Ensure the endpoint matches your FastAPI setup, including the base URL if needed
+            const response = await fetch(`/classify_text?input=${encodeURIComponent(text)}`);
+            if (!response.ok) {
+                throw new Error('Network response was not ok.');
+            }
+            const data = await response.json();
+            return data; // Return the entire response data
+        } catch (error) {
+            console.error("Error:", error);
+            return { sentiment: "Failed to classify text. Please try again later." };
+        }
+    };
+  
+    textClassForm.addEventListener("submit", async (event) => {
+        event.preventDefault();
+        const textClassInput = document.getElementById("text-class-input");
+        const sentimentParagraph = document.querySelector(".text-class-output");
+        const probabilityParagraph = document.querySelector(".probability-output"); // Add a selector for displaying probabilities
+  
+        // Display a loading message or similar feedback
+        sentimentParagraph.textContent = "Classifying text...";
+  
+        const { sentiment, positive_probability, negative_probability } = await classifyText(textClassInput.value);
+        
+        // Update the text content with the classification result and probabilities
+        sentimentParagraph.textContent = `Sentiment: ${sentiment}`;
+        probabilityParagraph.textContent = `Positive Probability: ${positive_probability.toFixed(2)}, Negative Probability: ${negative_probability.toFixed(2)}`;
+    });
+  });
+