OpenAI co-founder and Eureka Labs founder Andrej Karpathy has announced nanochat, an open-source project that provides a full training and inference pipeline for building ChatGPT-style models. The launch expands on his previous project, nanoGPT, which focused only on pretraining. With nanochat, users can now train and interact with their own large language model through a simple setup and web interface.
In a post on X, Karpathy wrote, “You boot up a cloud GPU box, run a single script and in as little as 4 hours later you can talk to your own LLM in a ChatGPT-like web UI.” The repository includes about 8,000 lines of code and features tokeniser training in Rust, Transformer LLM pretraining on FineWeb, supervised fine-tuning, and optional reinforcement learning using GRPO. It also enables efficient inference with KV caching and supports both command-line and web-based interaction.
Karpathy explained that nanochat allows flexible training options depending on time and cost. A basic ChatGPT-style model can be trained for approximately $100 in just 4 hours on an 8×H100 GPU node. A larger training run costing around $1,000 over 42 hours can produce a model capable of solving simple mathematical and coding problems.
He added, “My goal is to get the full ‘strong baseline’ stack into one cohesive, minimal, readable, hackable, maximally forkable repo.” Karpathy said that nanochat will also serve as the final project for his upcoming course, LLM101n, at Eureka Labs.
The release of nanochat is expected to make it easier for developers, researchers, and AI enthusiasts to understand, experiment with, and build their own LLMs, further promoting transparency and accessibility in artificial intelligence development.
Also read: Viksit Workforce for a Viksit Bharat
Do Follow: The Mainstream formerly known as CIO News LinkedIn Account | The Mainstream formerly known as CIO News Facebook | The Mainstream formerly known as CIO News Youtube | The Mainstream formerly known as CIO News Twitter |The Mainstream formerly known as CIO News Whatsapp Channel | The Mainstream formerly known as CIO News Instagram
About us:
The Mainstream formerly known as CIO News is a premier platform dedicated to delivering latest news, updates, and insights from the tech industry. With its strong foundation of intellectual property and thought leadership, the platform is well-positioned to stay ahead of the curve and lead conversations about how technology shapes our world. From its early days as CIO News to its rebranding as The Mainstream on November 28, 2024, it has been expanding its global reach, targeting key markets in the Middle East & Africa, ASEAN, the USA, and the UK. The Mainstream is a vision to put technology at the center of every conversation, inspiring professionals and organizations to embrace the future of tech.
