35 Topics
 | |
 | 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 … |
| | This tutorial demonstrates how to build an AI agent that queries SQLite databases using natural language. You will see how to leverage the [LangGraph framework](https://www.langchain.com/langgraph) and the [OpenAI GPT-4o](https://openai.com/index/gpt-4/) model to retrieve natural language answers from an SQLite database, given a natural language query. So, let's begin without ado. ## … |
| | 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 … |
| | In my previous article, I explained how to fine-tune [OpenAI GPT-4o model for natural language processing tasks](https://www.daniweb.com/programming/computer-science/tutorials/542333/how-to-fine-tune-the-openai-gpt-4o-model-the-wait-is-finally-over). In OpenAI DevDay, held on October 1, 2024, OpenAI announced that users can now fine-tune OpenAI vision and multimodal models such as GPT-4o and GPT-4o mini. The best part is that fine-tuning vision …  |
| | 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 … |
| | Open-source LLMs are gaining significant traction due to their ability to match the performance of advanced proprietary LLMs. These models are free to use and allow users to modify their source code or fine-tune them on their own systems, making them highly versatile for various applications. Alibaba's [Qwen](https://www.alibabacloud.com/en/solutions/generative-ai/qwen?_p_lc=1) and Meta's … |
| | 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 my previous article, I presented a [comparison of GPT-4o and Claude 3.5 Sonnet for multi-label text classification](https://www.daniweb.com/programming/computer-science/tutorials/542629/openai-gpt-4o-vs-claude-3-5-sonnet-for-multi-label-text-classification). The accuracies achieved by both models were relatively low. Fine-tuning is one solution to overcome the low performance of large-language models. With fine-tuning, you can incorporate custom domain knowledge into an LLM's … |
| | 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 … |
| | Open-source LLMS, owing to their comparable performance with advanced proprietary LLMs, have been gaining immense popularity lately. Open-source LLMs are free to use, and you can easily modify their source code or fine-tune them on your systems. [Alibaba's Qwen](https://www.alibabacloud.com/en/solutions/generative-ai/qwen?_p_lc=1) and [Meta's Llama](https://ai.meta.com/blog/meta-llama-3-1/) series of models are two major players in … |
| | 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 … |
| | Large language models (LLMS) are trained to predict the next token (set of characters) following an input sequence of tokens. This makes LLMs suitable for unstructured textual responses. However, we often need to extract structured information from unstructured text. With the Python [LangChain](https://www.langchain.com/) module, you can extract structured information in … |
| | On August 20, 2024, [OpenAI enabled GPT-4o fine-tuning](https://openai.com/index/gpt-4o-fine-tuning/) in the OpenAI playground and the OpenAI API. The much-awaited feature is free for fine-tuning 1 million daily tokens until September 23, 2024. In this article, I will show you how to fine-tune the OpenAI GPT-4o model for text classification and summarization … |
| | In a previous article, I compared [GPT-4o mini vs. GPT-4o and GPT-3.5 Turbo for zero-shot text summarization](https://www.daniweb.com/programming/computer-science/tutorials/542208/gpt-4o-mini-vs-gpt-4o-vs-gpt-3-5-turbo-for-text-summarization). The results showed that the GPT-4o mini achieves almost similar performance for zero-shot text classification at a much-reduced price compared to the other models. I will compare Meta Llama 3.1 70b with OpenAI … |
| | In my previous articles, I presented a [comparison of OpenAI GPT-4o mini model with GPT-4o and GPT-3.5 turbo models for zero-shot text classification](https://www.daniweb.com/programming/computer-science/tutorials/542182/gpt-4o-mini-a-cheaper-and-faster-alternative-to-gpt-4o). The results showed that GPT-4o mini, while significantly cheaper than its counterparts, achieves comparable performance. On 8 August 2024, OpenAI enabled GPT-4o mini fine-tuning for developers across … |
| | In my previous [article on GPT-4o mini](https://www.daniweb.com/programming/computer-science/tutorials/542182/gpt-4o-mini-a-cheaper-and-faster-alternative-to-gpt-4o), I compared the performance of GPT-4o mini against GPT-3.5 Turbo and GPT-4o for zero-shot text classification. We saw that GPT-4o mini, being 36% times cheaper, achieves only 2% less accuracy than GPT-4o. Furthermore, while being 1/3 of the price, the GPT-4o mini significantly … |
| | On July 18th, 2024, [OpenAI released GPT-4o mini](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/), their most cost-efficient small model. GPT-4o mini is around 60% cheaper than GPT-3.5 Turbo and around 97% cheaper than GPT-4o. As per OpenAI, GPT-4o mini outperforms GPT-3.5 Turbo on almost all benchmarks while being cheaper. In this article, we will compare the … |
| | On June 20, 2024, Anthropic released the [Claude 3.5 sonnet](https://www.anthropic.com/news/claude-3-5-sonnet) large language model. Claude claims it to be the state-of-the-art model for many natural language processing tasks, surpassing the [OpenAI GPT-4o model](https://openai.com/index/hello-gpt-4o/). My first test for comparing two large language models is their zero-shot text classification ability. In this article, … |
| | # Comparison Between Fine-tuned and Default GPT-3 Turbo for Text Classification In one of my previous articles, I showed you how to perform [zero-shot text classification using OpenAI GPT-4o and Meta Llama 3 models](https://www.daniweb.com/programming/computer-science/tutorials/542001/openai-gpt-4o-vs-meta-llama-3-for-zero-shot-text-classifiation). I used the default models for predicting sentiments of airline tweets. The default models perform substantially … |
| | 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 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 … |
 | **Discover the world of AI scams and find out how you can shield yourself against the cunning deceptions of deepfakes.**  In an incident that underscores the alarming capabilities of artificial intelligence in the realm of fraud, a company in Hong Kong was [defrauded of $25 million](https://www.businessinsider.com/deepfake-coworkers-video-call-company-loses-millions-employee-ai-2024-2) earlier this year. … |
| | On February 21, 2024, Google released [Gemma](https://ai.google.dev/gemma), a family of state-of-the-art open-source large language models (LLMs). As per initial results, its 7b (seven billion parameter) version is known to perform better than Meta's [Llama 2](https://llama.meta.com/), the previous state-of-the-art open-source LLM. As always, my first test with any new open-source LLM … |
| | Integrating language models like ChatGPT into third-party applications has become increasingly popular due to their ability to comprehend and generate human-like text. However, it's crucial to acknowledge the limitations of ChatGPT, such as its knowledge cut-off date in September 2021 and its inability to access external sources like Wikipedia or … |
| | **Tracing AI-generated content in online news articles with corpus linguistics**  *A query in the 'News on the Web' Corpus reveals that the use of the word 'tapestry' in online articles has more than doubled last year – from 3,085 instances in 2022 to 7,891 instances in 2023* “Today, we … |
| | 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 … |
| | ## Introduction ## This tutorial explains how to perform multiple-label text classification using the [Hugging Face](https://huggingface.co/) transformers library. Hugging Face library implements advanced transformer architectures, proven to be state-of-the-art for various natural language processing tasks, including text classification. Hugging Face library provides trainable transformer models in three flavors: 1. Via … |
| | Sentiment analysis, a subfield of Natural Language Processing (NLP), aims to discern and classify the underlying sentiment or emotion expressed in textual data. Whether it is understanding customers' opinions about a product, analyzing social media posts, or gauging public sentiment towards a political event, sentiment analysis plays a vital role … |
| | Facial emotion detection, as the name suggests, involves detecting emotions from faces in images or videos. Recently, I was working on a facial emotion detection task and came across the DeepFace library that implements various state-of-the-art facial emotion detection models. However, in my experience, the performance of the DeepFace library … |
| | In this tutorial, you will learn to fine-tune a [Hugging Face Transformers model](https://huggingface.co/docs/transformers/index) for video classification in PyTorch. The Hugging Face documentation provides an example of performing video classification using the Hugging Face Trainer with one of Hugging Face's built-in datasets. However, the process of fine-tuning a video transformer on … |
| | In a previous article, I showed you [how to analyze sentiments using Chat-GPT and data augmentation techniques](https://www.daniweb.com/programming/computer-science/tutorials/540502/sentiment-analysis-with-data-augmentation-using-chatgpt#post2293643). Following that, some readers reached out, asking for a breakdown of fine-tuning a Chat-GPT model. In this article, I will guide you through fine-tuning your Chat-GPT model using your own data. First, I'll … |
 | In my recent journey of developing various AI solutions powered by Language Models (LLMs), a significant question has emerged: Should we harness the capabilities of Retrieval Augmented Generation (RAG), or should we opt for the path of custom fine-tuning? This decision can profoundly impact the performance and adaptability of our … |
| | Data annotation for text classification is time-consuming and expensive. In the case of smaller training datasets, pre-trained ChatGPT models might achieve higher classification accuracy on test sets than training classifiers from scratch or fine-tuning existing models. Additionally, ChatGPT can aid in annotating data for fine-tuning text classification models. In this …  |