--- base_model: distilbert/distilbert-base-uncased-finetuned-sst-2-english library_name: sentence-transformers metrics: - pearson_cosine - spearman_cosine - pearson_manhattan - spearman_manhattan - pearson_euclidean - spearman_euclidean - pearson_dot - spearman_dot - pearson_max - spearman_max pipeline_tag: sentence-similarity tags: - sentence-transformers - sentence-similarity - feature-extraction - generated_from_trainer - dataset_size:302 - loss:CosineSimilarityLoss widget: - source_sentence: "interface Input {\n id: number;\n title: string;\n parent_id:\ \ number | null; \n}\n\ninterface Output extends Input {\n children?: Output[];\ \ \n}\n\nfunction doJob(inputItems: Input[], parent_id?: number) {\n const outputItems:\ \ Output[] = [];\n\n for (let i = 0; i < inputItems.length; i++) {\n const\ \ children = doJob(inputItems.slice(i, inputItems.length), inputItems[i].parent_id)\n\ \ .filter(i => i.parent_id === parent_id);\n \n outputItems.push({...item,\ \ children});\n }\n\n return outputItems;\n}" sentences: - "interface Task {\n id: number;\n title: string;\n parent_id: number\ \ | null;\n children?: Task[];\n}\n\nfunction buildTaskTree(tasks: Task[]):\ \ Task[] {\n const tasksMap = tasks.reduce((acc, task) => {\n acc[task.id]\ \ = { ...task, children: [] };\n return acc;\n }, {} as { [key: number]:\ \ Task });\n\n const rootTasks: Task[] = [];\n\n tasks.forEach(task => {\n\ \ const { id, parent_id } = task;\n if (parent_id === null) {\n\ \ rootTasks.push(tasksMap[id]);\n } else {\n if (tasksMap[parent_id])\ \ {\n tasksMap[parent_id].children.push(tasksMap[id]);\n \ \ }\n }\n });\n\n return rootTasks;\n}\n\n// Test the function\ \ with the provided example\nconst inputTasks: Task[] = [\n { id: 1, title:\ \ 'Task 1', parent_id: null },\n { id: 2, title: 'Task 2', parent_id: 1 },\n\ \ { id: 3, title: 'Task 3', parent_id: 1 }\n];\nconst outputTasks: Task[] =\ \ buildTaskTree(inputTasks);\nconsole.log(outputTasks);\n" - "const http = require('http');\n\nasync function checkUrlsStatus(urls) {\n \ \ const statusObj = {};\n\n const getStatus = async (url) => {\n return\ \ new Promise((resolve) => {\n http.get(url, (res) => {\n \ \ resolve(res.statusCode);\n }).on('error', (error) => {\n \ \ resolve(500); // Internal Server Error\n });\n \ \ });\n };\n\n await Promise.all(urls.map(async (url) => {\n const\ \ status = await getStatus(url);\n statusObj[url] = status;\n }));\n\ \n return statusObj;\n}\n\n// Example\nconst urls = ['https://example.com',\ \ 'https://google.com'];\ncheckUrlsStatus(urls)\n .then((result) => {\n \ \ console.log(result);\n })\n .catch((error) => {\n console.error(error);\n\ \ });\n\nmodule.exports = checkUrlsStatus;\n" - "def find_longest_word(words):\n max_length = 0\n longest_word = ''\n\n\ \ for word in words:\n if len(word) > max_length:\n max_length\ \ = len(word)\n longest_word = word\n\n return longest_word, max_length\n\ \n# Test cases\nprint(find_longest_word(['hello', 'world', 'python', 'programming']))\ \ # Output: ('programming', 11)\nprint(find_longest_word(['short', 'longer',\ \ 'longest', 'size'])) # Output: ('longest', 7)\n" - source_sentence: "// inventory.module.ts\nimport { Module } from '@nestjs/common';\n\ import { InventoryService } from './inventory.service';\nimport { InventoryController\ \ } from './inventory.controller';\nimport { TypeOrmModule } from '@nestjs/typeorm';\n\ import { Product } from './product.entity';\n@Module({\n imports: [TypeOrmModule.forFeature([Product])],\n\ \ providers: [InventoryService],\n controllers: [InventoryController],\n})\n\ export class InventoryModule {}\n// inventory.service.ts\nimport { Injectable\ \ } from '@nestjs/common';\nimport { InjectRepository } from '@nestjs/typeorm';\n\ import { Product } from './product.entity';\nimport { CreateProductDto, UpdateProductDto\ \ } from './product.dto';\n\n@Injectable()\nexport class InventoryService {\n\ \ constructor(\n @InjectRepository(Product)\n private readonly productRepository:\ \ Repository,\n ) {}\n\n async createProduct(createProductDto: CreateProductDto):\ \ Promise {\n const newProduct = new Product();\n newProduct.name\ \ = createProductDto.name;\n newProduct.description = createProductDto.description;\n\ \ newProduct.price = createProductDto.price;\n newProduct.availableQuantity\ \ = createProductDto.availableQuantity;\n\n return await this.productRepository.save(newProduct);\n\ \ }\n\n async updateProduct(\n productId: number,\n updateProductDto:\ \ UpdateProductDto,\n ): Promise {\n const product = await this.productRepository.findOne(productId);\n\ \ if (!product) {\n throw new NotFoundException('Product not found');\n\ \ }\n\n product.name = updateProductDto.name || product.name;\n product.description\ \ = updateProductDto.description || product.description;\n product.price =\ \ updateProductDto.price || product.price;\n product.availableQuantity =\n\ \ updateProductDto.availableQuantity || product.availableQuantity;\n\n \ \ return await this.productRepository.save(product);\n }\n\n async findAllProducts():\ \ Promise {\n return await this.productRepository.find();\n }\n\ \n async getProductById(productId: number): Promise {\n const product\ \ = await this.productRepository.findOne(productId);\n if (!product) {\n \ \ throw new NotFoundException('Product not found');\n }\n return product;\n\ \ }\n\n async checkProductAvailability(productId: number, quantity: number):\ \ Promise {\n const product = await this.productRepository.findOne(productId);\n\ \ if (!product) {\n throw new NotFoundException('Product not found');\n\ \ }\n return product.availableQuantity >= quantity;\n }\n}" sentences: - "// inventory.dto.ts\nimport { IsInt, IsNotEmpty, IsNumber, IsString, Min } from\ \ 'class-validator';\n\nexport class ProductDto {\n @IsString()\n @IsNotEmpty()\n\ \ id: string;\n\n @IsString()\n @IsNotEmpty()\n name: string;\n\n @IsString()\n\ \ description: string;\n\n @IsNumber()\n @IsNotEmpty()\n price: number;\n\n\ \ @IsInt()\n @Min(0)\n @IsNotEmpty()\n availableQuantity: number;\n}\n\n//\ \ inventory.interface.ts\nexport interface Product {\n id: string;\n name: string;\n\ \ description: string;\n price: number;\n availableQuantity: number;\n}\n\n\ // inventory.module.ts\nimport { Module } from '@nestjs/common';\nimport { TypeOrmModule\ \ } from '@nestjs/typeorm';\nimport { InventoryController } from './inventory.controller';\n\ import { InventoryService } from './inventory.service';\nimport { Product } from\ \ './product.entity';\n\n@Module({\n imports: [TypeOrmModule.forFeature([Product])],\n\ \ controllers: [InventoryController],\n providers: [InventoryService]\n})\n\ export class InventoryModule {} \n\n// product.entity.ts\nimport { Entity, Column,\ \ PrimaryGeneratedColumn } from 'typeorm';\n\n@Entity()\nexport class Product\ \ {\n @PrimaryGeneratedColumn()\n id: number;\n\n @Column()\n name: string;\n\ \n @Column()\n description: string;\n\n @Column('decimal')\n price: number;\n\ \n @Column()\n availableQuantity: number;\n}\n\n// inventory.controller.ts\n\ import { Controller, Get, Post, Put, Body, Param } from '@nestjs/common';\nimport\ \ { InventoryService } from './inventory.service';\nimport { ProductDto } from\ \ './inventory.dto';\n\n@Controller('inventory')\nexport class InventoryController\ \ {\n constructor(private readonly inventoryService: InventoryService) {}\n\n\ \ @Post('add-product')\n async addProduct(@Body() productDto: ProductDto) {\n\ \ return this.inventoryService.addProduct(productDto);\n }\n\n @Get('products')\n\ \ async getProducts() {\n return this.inventoryService.getProducts();\n }\n\ \n @Put('update-quantity/:id')\n async updateQuantity(@Param('id') id: string,\ \ @Body('quantity') quantity: number) {\n return this.inventoryService.updateQuantity(id,\ \ quantity);\n }\n}\n\n// inventory.service.ts\nimport { Injectable } from '@nestjs/common';\n\ import { InjectRepository } from '@nestjs/typeorm';\nimport { Repository } from\ \ 'typeorm';\nimport { Product } from './product.entity';\nimport { ProductDto\ \ } from './inventory.dto';\n\n@Injectable()\nexport class InventoryService {\n\ \ constructor(\n @InjectRepository(Product)\n private productRepository:\ \ Repository,\n ) {}\n\n async addProduct(productDto: ProductDto):\ \ Promise {\n const newProduct = this.productRepository.create(productDto);\n\ \ return this.productRepository.save(newProduct);\n }\n\n async getProducts():\ \ Promise {\n return this.productRepository.find();\n }\n\n async\ \ updateQuantity(id: string, quantity: number): Promise {\n const\ \ product = await this.productRepository.findOne(id);\n if (!product) {\n \ \ throw new Error('Product not found');\n }\n\n product.availableQuantity\ \ = quantity;\n return this.productRepository.save(product);\n }\n}\n" - "def move_zeros_to_end(lst):\n zero_count = 0\n for i in range(len(lst)):\n\ \ if lst[i] != 0:\n lst[i], lst[zero_count] = lst[zero_count],\ \ lst[i]\n zero_count += 1\n\n# Test cases\nlst1 = [0, 1, 0, 3, 12]\n\ move_zeros_to_end(lst1)\nprint(lst1) # Output: [1, 3, 12, 0, 0]\n\nlst2 = [0,\ \ 0, 1]\nmove_zeros_to_end(lst2)\nprint(lst2) # Output: [1, 0, 0]\n" - "// inventory.dto.ts\nimport { IsInt, IsNotEmpty, IsNumber, IsString, Min } from\ \ 'class-validator';\n\nexport class ProductDto {\n @IsString()\n @IsNotEmpty()\n\ \ id: string;\n\n @IsString()\n @IsNotEmpty()\n name: string;\n\n @IsString()\n\ \ description: string;\n\n @IsNumber()\n @IsNotEmpty()\n price: number;\n\n\ \ @IsInt()\n @Min(0)\n @IsNotEmpty()\n availableQuantity: number;\n}\n\n//\ \ inventory.interface.ts\nexport interface Product {\n id: string;\n name: string;\n\ \ description: string;\n price: number;\n availableQuantity: number;\n}\n\n\ // inventory.module.ts\nimport { Module } from '@nestjs/common';\nimport { TypeOrmModule\ \ } from '@nestjs/typeorm';\nimport { InventoryController } from './inventory.controller';\n\ import { InventoryService } from './inventory.service';\nimport { Product } from\ \ './product.entity';\n\n@Module({\n imports: [TypeOrmModule.forFeature([Product])],\n\ \ controllers: [InventoryController],\n providers: [InventoryService]\n})\n\ export class InventoryModule {} \n\n// product.entity.ts\nimport { Entity, Column,\ \ PrimaryGeneratedColumn } from 'typeorm';\n\n@Entity()\nexport class Product\ \ {\n @PrimaryGeneratedColumn()\n id: number;\n\n @Column()\n name: string;\n\ \n @Column()\n description: string;\n\n @Column('decimal')\n price: number;\n\ \n @Column()\n availableQuantity: number;\n}\n\n// inventory.controller.ts\n\ import { Controller, Get, Post, Put, Body, Param } from '@nestjs/common';\nimport\ \ { InventoryService } from './inventory.service';\nimport { ProductDto } from\ \ './inventory.dto';\n\n@Controller('inventory')\nexport class InventoryController\ \ {\n constructor(private readonly inventoryService: InventoryService) {}\n\n\ \ @Post('add-product')\n async addProduct(@Body() productDto: ProductDto) {\n\ \ return this.inventoryService.addProduct(productDto);\n }\n\n @Get('products')\n\ \ async getProducts() {\n return this.inventoryService.getProducts();\n }\n\ \n @Put('update-quantity/:id')\n async updateQuantity(@Param('id') id: string,\ \ @Body('quantity') quantity: number) {\n return this.inventoryService.updateQuantity(id,\ \ quantity);\n }\n}\n\n// inventory.service.ts\nimport { Injectable } from '@nestjs/common';\n\ import { InjectRepository } from '@nestjs/typeorm';\nimport { Repository } from\ \ 'typeorm';\nimport { Product } from './product.entity';\nimport { ProductDto\ \ } from './inventory.dto';\n\n@Injectable()\nexport class InventoryService {\n\ \ constructor(\n @InjectRepository(Product)\n private productRepository:\ \ Repository,\n ) {}\n\n async addProduct(productDto: ProductDto):\ \ Promise {\n const newProduct = this.productRepository.create(productDto);\n\ \ return this.productRepository.save(newProduct);\n }\n\n async getProducts():\ \ Promise {\n return this.productRepository.find();\n }\n\n async\ \ updateQuantity(id: string, quantity: number): Promise {\n const\ \ product = await this.productRepository.findOne(id);\n if (!product) {\n \ \ throw new Error('Product not found');\n }\n\n product.availableQuantity\ \ = quantity;\n return this.productRepository.save(product);\n }\n}\n" - source_sentence: "// wage-input.dto.ts\nimport { IsNumber, IsPositive } from 'class-validator';\n\ \nexport class WageInputDto {\n @IsNumber()\n @IsPositive()\n hourlyWage: number;\n\ \n @IsNumber()\n @IsPositive()\n hoursWorked: number;\n}\n\n// It will handle\ \ the input validation too.\n\n\n// employee.controller.ts\nimport { Body, Controller,\ \ Post } from '@nestjs/common';\nimport { WageInputDto } from './dto/wage-input.dto';\n\ import { EmployeeService } from './employee.service';\n\n@Controller('employee')\n\ export class EmployeeController {\n constructor(private readonly employeeService:\ \ EmployeeService) {}\n\n @Post('/wage')\n async getWage(@Body() input: WageInputDto)\ \ {\n return this.employeeService.getWage(input);\n }\n}\n\n// employee.service.ts\n\ import { Injectable } from '@nestjs/common';\nimport { WageInputDto } from './dto/wage-input.dto';\n\ \nconst WEEKLY_HOURS = 40;\n\n@Injectable()\nexport class EmployeeService {\n\ \ async getWage(input: WageInputDto) {\n let weeklyHours = 0;\n let overTimeHours\ \ = 0;\n let weeklyWage = 0;\n\n const hasDoneOverTime = input.hoursWorked\ \ > WEEKLY_HOURS;\n\n if (hasDoneOverTime) {\n weeklyHours = WEEKLY_HOURS;\n\ \ overTimeHours = input.hoursWorked - WEEKLY_HOURS;\n } else {\n \ \ weeklyHours = input.hoursWorked;\n }\n\n weeklyWage = weeklyHours * input.hourlyWage;\n\ \n if (hasDoneOverTime) {\n weeklyWage = weeklyWage + overTimeHours *\ \ (input.hourlyWage * 1.5);\n }\n\n return { weeklyWage };\n }\n}" sentences: - "import { Controller, Post, Body, HttpException, HttpStatus } from '@nestjs/common';\n\ \ninterface WeeklyWageInput {\n hourlyWage: number;\n hoursWorked: number;\n\ }\n\n@Controller('calculate-weekly-wage')\nexport class WeeklyWageController {\n\ \ @Post()\n calculateWeeklyWage(@Body() data: WeeklyWageInput): { weeklyWage:\ \ number } {\n // Input validation\n if (data.hourlyWage <= 0 || data.hoursWorked\ \ <= 0 || !Number.isInteger(data.hoursWorked)) {\n throw new HttpException('Invalid\ \ input. Hourly wage must be positive and hours worked must be a positive integer',\ \ HttpStatus.BAD_REQUEST);\n }\n\n const regularHours = Math.min(data.hoursWorked,\ \ 40);\n const overtimeHours = Math.max(data.hoursWorked - 40, 0);\n\n const\ \ weeklyWage = (regularHours * data.hourlyWage) + (overtimeHours * (1.5 * data.hourlyWage));\n\ \n return { weeklyWage };\n }\n}\n" - "import { Pipe, PipeTransform } from '@angular/core';\n\n@Pipe({\n name: 'orderBy'\n\ })\nexport class OrderByPipe implements PipeTransform {\n transform(array: any[],\ \ key: string, order: 'asc' | 'desc'): any[] {\n if (!Array.isArray(array)\ \ || !key || (order !== 'asc' && order !== 'desc')) {\n console.error('Invalid\ \ input data');\n return array;\n }\n\n const compareFn = (a: any,\ \ b: any): number => {\n if (a[key] < b[key]) {\n return order ===\ \ 'asc' ? -1 : 1;\n }\n if (a[key] > b[key]) {\n return order\ \ === 'asc' ? 1 : -1;\n }\n return 0;\n };\n\n return array.slice().sort(compareFn);\n\ \ }\n}\n" - "public class PalindromeChecker {\n public static boolean isPalindrome(String\ \ str) {\n str = str.toLowerCase().replaceAll(\"[^a-zA-Z0-9]\", \"\");\n\ \ int left = 0;\n int right = str.length() - 1;\n \n \ \ while (left < right) {\n if (str.charAt(left) != str.charAt(right))\ \ {\n return false;\n }\n left++;\n \ \ right--;\n }\n \n return true;\n }\n \n \ \ public static void main(String[] args) {\n String input1 = \"A man, a\ \ plan, a canal: Panama\";\n String input2 = \"race a car\";\n \n\ \ System.out.println(\"Input: '\" + input1 + \"' Output: \" + isPalindrome(input1));\n\ \ System.out.println(\"Input: '\" + input2 + \"' Output: \" + isPalindrome(input2));\n\ \ }\n}\n" - source_sentence: 'FROM python:3.8 WORKDIR /app COPY helloworld.py . RUN pip install --no-cache-dir -r requirements.txt CMD ["python", "helloworld.py"] ## PYTHON PROGRAM helloworld.py print("Hello, World!") ## BUILD COMMAND docker build -t "python:helloworld" . docker run -itd --name python python:helloworld' sentences: - '# Use a slim Python base image for optimization FROM python:3.9-slim # Set the working directory inside the container WORKDIR /app # Copy the Python script into the container COPY hello.py /app/hello.py # Define the command to run the Python script CMD ["python", "/app/hello.py"] ' - "import java.util.HashMap;\n\npublic class Solution {\n public int[] twoSum(int[]\ \ nums, int target) {\n HashMap map = new HashMap<>();\n\ \n for (int i = 0; i < nums.length; i++) {\n int complement\ \ = target - nums[i];\n if (map.containsKey(complement)) {\n \ \ return new int[]{map.get(complement), i};\n }\n \ \ map.put(nums[i], i);\n }\n\n return new int[]{};\n }\n}\n\ \n// Example\nint[] array = new int[]{2, 7, 11, 15};\nint target = 9;\nSolution\ \ solution = new Solution();\nint[] result = solution.twoSum(array, target);\n" - "function stripHtmlTags(input) {\n if (!input) return '';\n\n const tagRegex\ \ = /<[^>]*>/g;\n return input.replace(tagRegex, '');\n}\n" - source_sentence: "def move_zeroes(nums):\n count = 0\n for i in range(len(nums)):\n\ \ if nums[i] != 0:\n nums[count], nums[i]= nums[i], nums[count]\n \ \ count += 1\n for i in range(count, len(nums)):\n nums[i] =0\n\ninput =\ \ [int(x) for x in input(\"Enter integers separated by spaces: \").split()]\n\ move_zeroes(input)\n\nprint(input)" sentences: - "import 'package:flutter/material.dart';\nimport 'package:firebase_core/firebase_core.dart';\n\ import 'package:firebase_auth/firebase_auth.dart';\nimport 'package:firebase_database/firebase_database.dart';\n\ \nvoid main() async {\n WidgetsFlutterBinding.ensureInitialized();\n await Firebase.initializeApp();\n\ \ runApp(MyApp());\n}\n\nclass MyApp extends StatelessWidget {\n final databaseRef\ \ = FirebaseDatabase.instance.reference().child('messages');\n\n @override\n\ \ Widget build(BuildContext context) {\n return MaterialApp(\n home:\ \ Scaffold(\n appBar: AppBar(\n title: Text('Real-Time Messages'),\n\ \ ),\n body: MessagesList(databaseRef: databaseRef),\n floatingActionButton:\ \ AddMessageButton(databaseRef: databaseRef),\n ),\n );\n }\n}\n\nclass\ \ MessagesList extends StatelessWidget {\n final DatabaseReference databaseRef;\n\ \n MessagesList({required this.databaseRef});\n\n @override\n Widget build(BuildContext\ \ context) {\n return StreamBuilder(\n stream: databaseRef.orderByChild('timestamp').onValue,\n\ \ builder: (context, snapshot) {\n if (snapshot.hasError) {\n \ \ return Text('Error: ${snapshot.error}');\n }\n\n if (!snapshot.hasData)\ \ {\n return Center(child: CircularProgressIndicator());\n }\n\ \n List messages = [];\n snapshot.data!.snapshot.value.forEach((key,\ \ value) {\n messages.add(Message.fromMap(value));\n });\n \ \ messages.sort((a, b) => a.timestamp.compareTo(b.timestamp));\n\n \ \ return ListView.builder(\n itemCount: messages.length,\n itemBuilder:\ \ (context, index) {\n return ListTile(\n title: Text(messages[index].text),\n\ \ );\n },\n );\n },\n );\n }\n}\n\nclass AddMessageButton\ \ extends StatelessWidget {\n final DatabaseReference databaseRef;\n\n AddMessageButton({required\ \ this.databaseRef});\n\n @override\n Widget build(BuildContext context) {\n\ \ return FloatingActionButton(\n onPressed: () {\n databaseRef.push().set({\n\ \ 'text': 'New Message',\n 'timestamp': DateTime.now().millisecondsSinceEpoch\n\ \ });\n },\n child: Icon(Icons.add),\n );\n }\n}\n\nclass\ \ Message {\n final String text;\n final int timestamp;\n\n Message({required\ \ this.text, required this.timestamp});\n\n factory Message.fromMap(Map map) {\n return Message(\n text: map['text'],\n timestamp:\ \ map['timestamp'],\n );\n }\n}\n" - "using System;\nusing System.Collections.Generic;\n\nclass BracketChecker\n{\n\ \ private readonly Dictionary bracketPairs = new Dictionary\n {\n { '(', ')' },\n { '[', ']' },\n { '{', '}'\ \ }\n };\n\n public bool CheckBalancedBrackets(string input)\n {\n \ \ if (string.IsNullOrEmpty(input))\n {\n return true;\n\ \ }\n\n Stack stack = new Stack();\n\n foreach\ \ (char c in input)\n {\n if (bracketPairs.ContainsValue(c))\n\ \ {\n if (stack.Count == 0 || bracketPairs[stack.Peek()]\ \ != c)\n {\n return false;\n \ \ }\n stack.Pop();\n }\n else if (bracketPairs.ContainsKey(c))\n\ \ {\n stack.Push(c);\n }\n }\n\n \ \ return stack.Count == 0;\n }\n}\n\nclass Program\n{\n static void\ \ Main()\n {\n BracketChecker bracketChecker = new BracketChecker();\n\ \n string input1 = \"(a+[b*c]-{d/e})\";\n Console.WriteLine(\"Input:\ \ \\\"{0}\\\"\", input1);\n Console.WriteLine(\"Output: {0}\\n\", bracketChecker.CheckBalancedBrackets(input1));\n\ \n string input2 = \"(a+[b*c)-{d/e}]\";\n Console.WriteLine(\"Input:\ \ \\\"{0}\\\"\", input2);\n Console.WriteLine(\"Output: {0}\", bracketChecker.CheckBalancedBrackets(input2));\n\ \ }\n}\n" - "def move_zeros_to_end(lst):\n zero_count = 0\n for i in range(len(lst)):\n\ \ if lst[i] != 0:\n lst[i], lst[zero_count] = lst[zero_count],\ \ lst[i]\n zero_count += 1\n\n# Test cases\nlst1 = [0, 1, 0, 3, 12]\n\ move_zeros_to_end(lst1)\nprint(lst1) # Output: [1, 3, 12, 0, 0]\n\nlst2 = [0,\ \ 0, 1]\nmove_zeros_to_end(lst2)\nprint(lst2) # Output: [1, 0, 0]\n" model-index: - name: SentenceTransformer based on distilbert/distilbert-base-uncased-finetuned-sst-2-english results: - task: type: semantic-similarity name: Semantic Similarity dataset: name: Unknown type: unknown metrics: - type: pearson_cosine value: 0.9000341656513303 name: Pearson Cosine - type: spearman_cosine value: 0.9013693287916293 name: Spearman Cosine - type: pearson_manhattan value: 0.8619949591168187 name: Pearson Manhattan - type: spearman_manhattan value: 0.8020438201628594 name: Spearman Manhattan - type: pearson_euclidean value: 0.868483180326987 name: Pearson Euclidean - type: spearman_euclidean value: 0.8234464507775442 name: Spearman Euclidean - type: pearson_dot value: 0.8494699061913786 name: Pearson Dot - type: spearman_dot value: 0.8947516297094024 name: Spearman Dot - type: pearson_max value: 0.9000341656513303 name: Pearson Max - type: spearman_max value: 0.9013693287916293 name: Spearman Max --- # SentenceTransformer based on distilbert/distilbert-base-uncased-finetuned-sst-2-english This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [distilbert/distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert/distilbert-base-uncased-finetuned-sst-2-english) - **Maximum Sequence Length:** 512 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DistilBertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("wasabibish/similarity-code-ai-generated") # Run inference sentences = [ 'def move_zeroes(nums):\n count = 0\n for i in range(len(nums)):\n if nums[i] != 0:\n nums[count], nums[i]= nums[i], nums[count]\n count += 1\n for i in range(count, len(nums)):\n nums[i] =0\n\ninput = [int(x) for x in input("Enter integers separated by spaces: ").split()]\nmove_zeroes(input)\n\nprint(input)', 'def move_zeros_to_end(lst):\n zero_count = 0\n for i in range(len(lst)):\n if lst[i] != 0:\n lst[i], lst[zero_count] = lst[zero_count], lst[i]\n zero_count += 1\n\n# Test cases\nlst1 = [0, 1, 0, 3, 12]\nmove_zeros_to_end(lst1)\nprint(lst1) # Output: [1, 3, 12, 0, 0]\n\nlst2 = [0, 0, 1]\nmove_zeros_to_end(lst2)\nprint(lst2) # Output: [1, 0, 0]\n', 'using System;\nusing System.Collections.Generic;\n\nclass BracketChecker\n{\n private readonly Dictionary bracketPairs = new Dictionary\n {\n { \'(\', \')\' },\n { \'[\', \']\' },\n { \'{\', \'}\' }\n };\n\n public bool CheckBalancedBrackets(string input)\n {\n if (string.IsNullOrEmpty(input))\n {\n return true;\n }\n\n Stack stack = new Stack();\n\n foreach (char c in input)\n {\n if (bracketPairs.ContainsValue(c))\n {\n if (stack.Count == 0 || bracketPairs[stack.Peek()] != c)\n {\n return false;\n }\n stack.Pop();\n }\n else if (bracketPairs.ContainsKey(c))\n {\n stack.Push(c);\n }\n }\n\n return stack.Count == 0;\n }\n}\n\nclass Program\n{\n static void Main()\n {\n BracketChecker bracketChecker = new BracketChecker();\n\n string input1 = "(a+[b*c]-{d/e})";\n Console.WriteLine("Input: \\"{0}\\"", input1);\n Console.WriteLine("Output: {0}\\n", bracketChecker.CheckBalancedBrackets(input1));\n\n string input2 = "(a+[b*c)-{d/e}]";\n Console.WriteLine("Input: \\"{0}\\"", input2);\n Console.WriteLine("Output: {0}", bracketChecker.CheckBalancedBrackets(input2));\n }\n}\n', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] ``` ## Evaluation ### Metrics #### Semantic Similarity * Evaluated with [EmbeddingSimilarityEvaluator](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:-------------------|:-----------| | pearson_cosine | 0.9 | | spearman_cosine | 0.9014 | | pearson_manhattan | 0.862 | | spearman_manhattan | 0.802 | | pearson_euclidean | 0.8685 | | spearman_euclidean | 0.8234 | | pearson_dot | 0.8495 | | spearman_dot | 0.8948 | | pearson_max | 0.9 | | **spearman_max** | **0.9014** | ## Training Details ### Training Dataset #### Unnamed Dataset * Size: 302 training samples * Columns: sentence1, sentence2, and score * Approximate statistics based on the first 302 samples: | | sentence1 | sentence2 | score | |:--------|:------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details |
  • min: 3 tokens
  • mean: 206.43 tokens
  • max: 512 tokens
|
  • min: 27 tokens
  • mean: 244.9 tokens
  • max: 512 tokens
|
  • min: 0.0
  • mean: 0.29
  • max: 0.9
| * Samples: | sentence1 | sentence2 | score | |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------| | from django.views.generic import ListView

class PersonListView(ListView):
model = Person
template_name = 'person_list.html'

def get_queryset(self):
return Person.objects.filter(birthdate__year__lte=2005) | from myapp.models import Customer # Import the Customer model from your Django app

def get_customers_with_zip_code_starting_with_123():
customers = Customer.objects.filter(zip_code__startswith='123').values() # Query to filter customers with zip_code starting with '123'
return list(customers) # Return a list of dictionaries for matching records
 | 0.4 | |

Welcome to our website!



 | function createSentence(words, maxChars) {
if (words.length === 0 || maxChars < 1) {
return "";
}

let sentence = "";
let currentLength = 0;

for (let i = 0; i < words.length; i++) {
if (sentence.length + words[i].length + 1 <= maxChars) {
sentence += words[i] + " ";
currentLength += words[i].length + 1;
} else {
break;
}
}

if (sentence.length > 0) {
sentence = sentence.trim() + ".";
}

return sentence;
}

// Test the function with the example
const words = ['hello', 'world', 'this', 'is', 'a', 'test'];
const maxChars = 20;
console.log(createSentence(words, maxChars)); // Output: 'hello world this.'
 | 0.1 | | AAAAAA | #include
#include

class KMP {
public:
std::vector findPatternIndices(const CString& text, const CString& pattern) {
std::vector indices;
if (pattern.IsEmpty() || text.IsEmpty()) {
return indices;
}

std::vector lps = computeLPSArray(pattern);

int i = 0, j = 0;
while (i < text.GetLength()) {
if (pattern[j] == text[i]) {
j++;
i++;
}

if (j == pattern.GetLength()) {
indices.push_back(i - j);
j = lps[j - 1];
} else if (i < text.GetLength() && pattern[j] != text[i]) {
if (j != 0) {
j = lps[j - 1];
} else {
i++;
}
}
}

return indices;
}

private:
std::vector computeLPSArray(const CString& pattern) {
int len = 0;
std::vector lps(pattern.GetLength(), 0);

int i = 1;
while (i < pattern.GetLength()) {
if (pattern[i] == pattern[len]) {
len++;
lps[i] = len;
i++;
} else {
if (len != 0) {
len = lps[len - 1];
} else {
lps[i] = 0;
i++;
}
}
}

return lps;
}
};

void testKMP() {
KMP kmp;

CString text1 = "ABABDABACDABABCABAB";
CString pattern1 = "ABABCABAB";
std::vector result1 = kmp.findPatternIndices(text1, pattern1);
OutputDebugString("Input: text='ABABDABACDABABCABAB', pattern='ABABCABAB' -> Output: [");
for (int i = 0; i < result1.size(); i++) {
OutputDebugString(result1[i]);
if (i < result1.size() - 1) {
OutputDebugString(",");
}
}
OutputDebugString("]\n");

CString text2 = "AAAAA";
CString pattern2 = "AAA";
std::vector result2 = kmp.findPatternIndices(text2, pattern2);
OutputDebugString("Input: text='AAAAA', pattern='AAA' -> Output: [");
for (int i = 0; i < result2.size(); i++) {
OutputDebugString(result2[i]);
if (i < result2.size() - 1) {
OutputDebugString(",");
}
}
OutputDebugString("]\n");
}
 | 0.0 | * Loss: [CosineSimilarityLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "loss_fct": "torch.nn.modules.loss.MSELoss" } ``` ### Evaluation Dataset #### Unnamed Dataset * Size: 76 evaluation samples * Columns: sentence1, sentence2, and score * Approximate statistics based on the first 76 samples: | | sentence1 | sentence2 | score | |:--------|:------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details |
  • min: 5 tokens
  • mean: 216.92 tokens
  • max: 512 tokens
|
  • min: 54 tokens
  • mean: 254.78 tokens
  • max: 512 tokens
|
  • min: 0.0
  • mean: 0.33
  • max: 0.9
| * Samples: | sentence1 | sentence2 | score | |:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------| | function stripHtmlTags(str) {
return str.replace(/<[^>]*>/g, '');
}

const input = '

Hello World!

';

const output = stripHtmlTags(input);

console.log(output); | function stripHtmlTags(input) {
if (!input) return '';

const tagRegex = /<[^>]*>/g;
return input.replace(tagRegex, '');
}
 | 0.6 | | function getTopThreeWords($text) {
// Remove punctuation and convert to lowercase
$words = str_word_count(strtolower(preg_replace('/[^\p{L}\p{N}\s]/u', ' ', $text)), 1);

// Count the frequency of each word
$wordFrequency = array_count_values($words);

// Sort the words by frequency in descending order
arsort($wordFrequency);

// Get the top three words
$topThreeWords = array_slice($wordFrequency, 0, 3, true);

// Format the output
$output = [];
foreach ($topThreeWords as $word => $count) {
$output[] = "('$word', $count)";
}

return '[' . implode(', ', $output) . ']';
}

// Example usage:
$inputText = "The quick brown fox jumps over the lazy dog. The dog was lazy!";
echo getTopThreeWords($inputText);
?> |
function countTopWords($inputString) {
// Convert the input string to lowercase and remove punctuation
$cleanString = preg_replace("/[\W_]+/", " ", strtolower($inputString));

// Split the string into an array of words
$words = explode(" ", $cleanString);

// Count the frequency of each word
$wordCount = array_count_values($words);

// Sort the words by frequency in descending order
arsort($wordCount);

// Get the top three most common words
$topWords = array_slice($wordCount, 0, 3);

// Format the output as an array of tuples
$output = [];
foreach ($topWords as $word => $count) {
$output[] = [$word, $count];
}

return $output;
}

// Test the function with the example input
$inputString = "The quick brown fox jumps over the lazy dog. The dog was lazy!";
$output = countTopWords($inputString);
print_r($output);

?>
 | 0.3 | | AAAAAA | #include
#include

class KMP {
public:
std::vector findPatternIndices(const CString& text, const CString& pattern) {
std::vector indices;
if (pattern.IsEmpty() || text.IsEmpty()) {
return indices;
}

std::vector lps = computeLPSArray(pattern);

int i = 0, j = 0;
while (i < text.GetLength()) {
if (pattern[j] == text[i]) {
j++;
i++;
}

if (j == pattern.GetLength()) {
indices.push_back(i - j);
j = lps[j - 1];
} else if (i < text.GetLength() && pattern[j] != text[i]) {
if (j != 0) {
j = lps[j - 1];
} else {
i++;
}
}
}

return indices;
}

private:
std::vector computeLPSArray(const CString& pattern) {
int len = 0;
std::vector lps(pattern.GetLength(), 0);

int i = 1;
while (i < pattern.GetLength()) {
if (pattern[i] == pattern[len]) {
len++;
lps[i] = len;
i++;
} else {
if (len != 0) {
len = lps[len - 1];
} else {
lps[i] = 0;
i++;
}
}
}

return lps;
}
};

void testKMP() {
KMP kmp;

CString text1 = "ABABDABACDABABCABAB";
CString pattern1 = "ABABCABAB";
std::vector result1 = kmp.findPatternIndices(text1, pattern1);
OutputDebugString("Input: text='ABABDABACDABABCABAB', pattern='ABABCABAB' -> Output: [");
for (int i = 0; i < result1.size(); i++) {
OutputDebugString(result1[i]);
if (i < result1.size() - 1) {
OutputDebugString(",");
}
}
OutputDebugString("]\n");

CString text2 = "AAAAA";
CString pattern2 = "AAA";
std::vector result2 = kmp.findPatternIndices(text2, pattern2);
OutputDebugString("Input: text='AAAAA', pattern='AAA' -> Output: [");
for (int i = 0; i < result2.size(); i++) {
OutputDebugString(result2[i]);
if (i < result2.size() - 1) {
OutputDebugString(",");
}
}
OutputDebugString("]\n");
}
 | 0.0 | * Loss: [CosineSimilarityLoss](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters: ```json { "loss_fct": "torch.nn.modules.loss.MSELoss" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `weight_decay`: 0.2 - `max_steps`: 100 - `warmup_steps`: 150 #### All Hyperparameters
Click to expand - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: True - `per_device_train_batch_size`: 8 - `per_device_eval_batch_size`: 8 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `torch_empty_cache_steps`: None - `learning_rate`: 5e-05 - `weight_decay`: 0.2 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 3.0 - `max_steps`: 100 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.0 - `warmup_steps`: 150 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `restore_callback_states_from_checkpoint`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: False - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: False - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_eval_metrics`: False - `eval_on_start`: False - `eval_use_gather_object`: False - `batch_sampler`: batch_sampler - `multi_dataset_batch_sampler`: proportional
### Training Logs | Epoch | Step | loss | spearman_max | |:------:|:----:|:------:|:------------:| | 0.5263 | 20 | 0.3765 | 0.5421 | | 1.0526 | 40 | 0.1518 | 0.5774 | | 1.5789 | 60 | 0.0501 | 0.8533 | | 2.1053 | 80 | 0.0217 | 0.8900 | | 2.6316 | 100 | 0.0168 | 0.9014 | ### Framework Versions - Python: 3.9.10 - Sentence Transformers: 3.1.0 - Transformers: 4.44.2 - PyTorch: 2.4.1+cpu - Accelerate: 0.34.2 - Datasets: 3.0.0 - Tokenizers: 0.19.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ```