Blog
How 15 top LLMs perform on classification: accuracy vs. cost breakdown
In this post, we explore and compare how LLMs perform on classification tasks.
How OpenAI's o1 changes the LLM training picture - Part 2
What makes o1 different from previous state-of-the-art LLMs?
How OpenAI's o1 changes the LLM training picture - Part 1
What makes o1 different from previous state-of-the-art LLMs?
Introducing AI-powered classification and labeling
We are launching a new feature to help you label and classify your unstructured datasets.
Introducing Fineweb-Edu-Fortified, an open dataset of high-quality educational web content
The finest collection of educational content the web has to offer, deduplicated and augmented with embeddings.
Airtrain PRO: A Comprehensive Toolkit For Advanced Data Exploration
Learn more about Airtrain PRO, a subscription plan built for data professionals.
How Airtrain Clusters Textual Data
At Airtrain, we aim to help people make sense of their unstructured text data, whether it is to build datasets for LLM fine-tuning, evaluation sets, or just figuring out how people are using their products.
The LLM Playground: March 2024 release and Product Hunt launch
Read about our latest Playground features and how to support our Product Hunt launch.
The Airtrain Playground: Match up Mistral, Gemini, GPT-4, Phi-2, Llama 2 and more
The Airtrain Playground lets you interact with a large selection of open-source and proprietary LLMs.
Getting Started with the Gemini Pro API
This guide explores how to obtain an API key and get started with the Gemini Pro SDKs.
Embedding Based Evaluation Metrics: Strengths and Weaknesses
We explore existing embedding-based evaluation metrics and review their benefits and pitfalls.
Beyond OpenAI: Reasons, Timing, and Strategies for Exploring Alternatives
OpenAI's recent hurdles is a wake up call. AI leaders must explore alternatives to guarantee sustainable AI strategies.
Replicating Academic Benchmarks with Airtrain: MMLU
We show how Airtrain can easily replicate the MMLU benchmark results for the Llama 2 family of models.
The comprehensive guide to LLM evaluation
In this extensive guide to LLM evaluation. We cover all existing methods to gauge the quality of a language model.
Introducing Airtrain
We are very excited to introduce to you Airtrain, a no-code platform for evaluation and fine-tuning workloads.