30 Tutorial Topics
Remove Filter  | |
 | Large language models are trained on a fixed corpus, and their knowledge is often limited by the documents they are trained on. Techniques like retrieval augmented generation, continuous pre-training, and fine-tuning enhance an LLM's default knowledge. However, these techniques can still not enable an LLM to answer queries that require … |
| | On April 14, 2025, OpenAI released [GPT-4.1](https://openai.com/index/gpt-4-1/) — a model touted as the new state-of-the-art, outperforming GPT-4o on all major benchmarks. As always, I like to evaluate new LLMs on simple tasks like text classification and summarization to see how they compare with current leading models. In this article, I … |
| | In a [previous article](https://www.daniweb.com/programming/computer-science/tutorials/543028/text-classification-and-summarization-with-deepseek-r1-distill-llama-70b), I presented a comparison of [DeepSeek-R1-Distill-Llama-70b](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) with the [DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) for text classification and summarization. Both these models are distilled versions of the original DeepSeek R1 model. Recently, I wanted to try the original version of the DeepSeek R1 model using the DeepSeek API. However, I was … |
| | In the [last article](https://www.daniweb.com/programming/computer-science/tutorials/542973/benchmarking-deepseek-r1-for-text-classification-and-summarization#post2300447), I explained how you can use the [DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) model for text classification and summarization problems. In this article, we will use the [DeepSeek-R1-Distill-Llama-70b](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B) for the same tasks. Following results from the [DeepSeek-AI's official paper](https://arxiv.org/pdf/2501.12948) show that `DeepSeek-R1-Distill-Llama-70b` outperform the other distilled models on 4 out of … |
| | DeepSeek-R1 is a groundbreaking family of reinforcement learning (RL)-driven AI models developed by the Chinese AI firm [DeepSeek](https://www.deepseek.com/). It is designed to rival industry leaders like OpenAI and Google in complex decision-making and optimization problems. In this article, we will benchmark the DeepSeek R1 model for text classification and summarization … |
| | On November 20, 2024, OpenAI updated its GPT-4o model, claiming it is more creative and accurate on several benchmarks. In this article, I compare the GPT-4o November update with the previous version (August update) for text summarization and classification tasks. By the end of this article, you will see whether … |
| | In one of my previous articles, you saw a [comparison of GPT-4o vs. Claude 3.5 sonnet for zero-shot text classification](https://www.daniweb.com/programming/computer-science/tutorials/542132/comparing-gpt-4o-vs-claude-3-5-sonnet-for-zero-shot-text-classification). In that article; we performed multi-class text classification where input tweets belonged to one of the three categories. In this article, we will go a step further and perform zero-shot … |
| | This article explains how to create a retrieval augmented generation (RAG) chatbot in LangChain using open-source models from [Hugging Face serverless inference API](https://huggingface.co/docs/api-inference/en/index). You will see how to call large language models (LLMs) and embedding models from Hugging Face serverless inference API using LangChain. You will also see how to … |
| | In one of my previous articles, I explained [how to generate stunning images for free using diffusion models](https://www.daniweb.com/programming/computer-science/tutorials/541898/generate-stunning-ai-images-for-free-using-diffusion-models) and showed how to generate Stability AI's diffusion models for text-to-image generation. Since then, the AI domain has progressed considerably, particularly in image generation. Black Forest Labs has released [Flux.1 series of …  |
| | On September 19, 2024, [Alibaba released the Qwen 2.5 series of models](https://qwenlm.github.io/blog/qwen2.5/). The Qwen 2.5-72B base and instruct models outperformed larger state-of-the-art models like Llama 3.1-405B on multiple benchmarks. It is safe to assume that Qwen 2.5-72B is a state-of-the-art open-source large language model. This article will show you how … |
| | Are you interested in finding out what a YouTube channel mostly discusses? Do you want to analyze YouTube videos of a specific channel? If yes, we are in the same boat. YouTube video titles are a great way to determine the channel's primary focus. Plotting a word cloud or a … |
| | On April 18, 2024, Meta AI released [Llama 3](https://ai.meta.com/blog/meta-llama-3/), which they claimed to be the most capable openly available LLM to date. Concurrently, OpenAI announced [GPT-4o (omni)](https://community.openai.com/t/announcing-gpt-4o-in-the-api/744700) on May 13, 2024, which is touted as the state-of-the-art proprietary model for various NLP benchmarks. As a guy who loves to compare … |
| | On March 4, 2024, [Anthropic](https://www.anthropic.com/) launched the [Claude 3 family of large language models](https://www.anthropic.com/news/claude-3-family). Anthropic claimed that its Claude 3 Opus model outperforms GPT-4 on various benchmarks. Intrigued by Anthropic's claim, I performed a simple test to compare the performances of Claude 3 Opus, [Google Gemini Pro](https://deepmind.google/technologies/gemini/#introduction), and [OpenAI's GPT-4](https://openai.com/research/gpt-4) … |
| | In the rapidly evolving field of Natural Language Processing (NLP), open-source large language models (LLMs) are becoming increasingly popular as they are free to use. Among these, the [Mistral](https://docs.mistral.ai/models/) family of models stands out as a state-of-the-art model that is freely accessible to the public. Comparable in performance to the … |
| | In a previous article, I explained [how to fine-tune Google's Gemma model for text classification](https://www.daniweb.com/programming/computer-science/tutorials/541544/fine-tuning-google-gemma-model-for-text-classification-in-python). In this article, I will explain how you can improve performance of a pretrained large language model (LLM) using retrieval augmented generation (RAG) technique. So, let's begin without ado. ## What is Retrieval Augmented Generation … |
| | In this article, we will compare two state-of-the-art large language models for zero-shot text classification: [Google Gemini Pro](https://deepmind.google/technologies/gemini/#introduction) and [OpenAI GPT-4](https://openai.com/research/gpt-4). Zero-shot text classification is a task where a model is trained on a set of labeled examples but can then classify new examples from previously unseen classes. This is … |
| | In a [previous tutorial](https://www.daniweb.com/programming/computer-science/tutorials/541123/stock-price-prediction-using-1d-cnn-in-tensorflow-keras), I covered how to predict future stock prices using a deep learning model with 1D CNN layers. This method is effective for basic time series forecasting. Recently, I've enhanced this model by not just considering past closing prices but also factors like Open, High, Low, Volume, … |
 | ## Introduction ## In Android Studio, we can run multiple tests in parallel across multiple devices using the dropdown menu.  Running instrumented tests this way is very convenient during development, but there is a problem with this method when your tests are run on a remote build server: * … |
| | ## Introduction ## While creating Selenium tests, you might have found that inspecting elements manually using the web browser’s inspector could be tedious. Even after you have found the element, you still have to go through the pain of looking up the correct **xpath** syntax for this specific element. To … |
| | ## Introduction ## The Android Paging 3 library can operate in two modes, with an offline Room database as a source of truth or without one. In this tutorial, we will look at how to use Paging 3 with a local Room database. This tutorial expands on the previously published … |
| | ## Introduction ## When working with Services on Android, you might have ran into an issue where you would like to: 1. Use a concrete implementation of a Service (*from a built-in or third party library*). 2. Make the Service lifecycle-aware so that you can use coroutines with it. Many … |
| | ## Introduction ## MediaPlayer (`android.media.MediaPlayer`) is a popular way to play media files, and combining it with a SeekBar can greatly improve the user experience. In this tutorial, we will learn how to synchronize a MediaPlayer progress to a SeekBar position. ## Goals ## At the end of the tutorial, … |
| | ## Introduction ## When working with a Room database, we are mostly restricted to save data using primitives (*and boxed primitives*). Reference types are not supported right out of the box, but can be enabled by creating additional [TypeConverter](https://developer.android.com/reference/androidx/room/TypeConverter). If you are familiar with ORM-light frameworks such as Spring JDBC, … |
| | ## Introduction ## The **Storage Access Framework** (SAF) provides a great way to access files exposed by other applications via their own DocumentProviders. In this tutorial, we will learn how to use the SAF in our App. ## Goals ## At the end of the tutorial, you would have learned: … |
| | ## Introduction ## UI Automator is a library that allows you to create tests that can interact with other components besides your App, such as Settings or other Android components. In this tutorial, we will learn how to incorporate UI Automator into our tests. ## Goals ## At the end … |
| | ## Introduction ## All TextView objects have a special attribute called `textAppearance`. This attribute can be used to set the style for text content in a TextView without affecting other styling attributes on the same TextView object. In this tutorial, we will learn how to apply `textAppearance` to TextView objects. … |
 | The Google Experience Launcher, as it was, first arrived exclusively for the Nexus 5 towards the end of last year. That changed recently when the renamed Google Now Launcher (GNL) appeared in the Play Store as a standalone app for Nexus devices and those handsets running Google Play Edition (GPE), …  |
| | There are two very obvious truths which need to be stated before going any further: Truth 1 - prevention is better than cure, so don't visit 'dodgy' sites or download anything anyone sends you a link to, and do keep your PC as secure as possible with the help of …  |
| | ## Contents ## Overview 1. Alternatives to Deprecated mysql_* Functions 2. SQL Injection: What to do with $_POST and $_GET variables 3. How to Insert Tablenames and Fieldnames Properly 4. What to do With Dynamic Values? 5. How to Use Aggregate Functions (COUNT, SUM, MIN etc) 6. How to Paginate …  |
| |  Whether you own a small personal blog or a top 1000 website, the importance of monetizing your website to the fullest is essential. Depending on your needs and the type of website you have, there are a variety of ways to improve your ability to monetize, simplify your … |