Tag

#fine-tuning

17 articles

Nvidia just showed that the harness, not the AI model, is now the real hero

Nvidia's research demonstrates that AI agents can perform well through fine-tuning and harness design, rather than relying solely on advanced models.

Aug 2129

Auditing Preference Biases and Fine-Tuning Language Models with Direct Preference Optimization on Anthropic HH-RLHF Using TRL and LoRA

This article explains Direct Preference Optimization (DPO), a method for fine-tuning language models using preference data, and how it can be implemented using TRL and LoRA tools. It also discusses the importance of auditing preference data for biases.

Aug 1920

Fine-Tuning Tool-Calling LLMs: A Complete Guide Using XYZ-Aquila-SFT and Qwen3

Learn how fine-tuning tool-calling language models helps AI systems use specific tools to perform real-world tasks more effectively.

Aug 1537

DeepSeek Upgrades DeepSeek-V4-Flash-0731 with Major Agentic and Coding Gains

This article explains how DeepSeek enhanced its DeepSeek-V4-Flash-0731 model through re-post-training, demonstrating how targeted fine-tuning can significantly improve AI capabilities in agentic reasoning and coding without changing the base architecture.

Jul 3182

tools

Unsloth vs Axolotl vs TRL vs LLaMA-Factory: A Fine-Tuning Framework Comparison on Speed, VRAM, and Multi-GPU

A comparison of four leading open-source LLM fine-tuning frameworks—Unsloth, Axolotl, TRL, and LLaMA-Factory—reveals their distinct approaches to speed, VRAM usage, and multi-GPU support.

Jul 2248

Someone Fine-Tuned OpenBMB’s MiniCPM5-1B on Claude Fable 5 Traces to Ship a 657MB Local Thinking Model

Learn how fine-tuning allows developers to create small, local AI models that can think and reason like larger systems, all while running on your own device.

Jul 1960

Fine-Tuning Qwen3 with LoRA Using NVIDIA NeMo AutoModel: A Complete Single-GPU Google Colab Workflow Tutorial

This article explains how to fine-tune the Qwen3 language model using Low-Rank Adaptation (LoRA) and NVIDIA NeMo AutoModel in a single-GPU Google Colab environment, focusing on parameter-efficient training techniques and automated workflows.

Jul 1858

I had Gemini and Claude write my email replies - but only one sounds like me

This article explains how language model fine-tuning and personalization work in AI systems, using the comparison between Gemini and Claude's email reply generation as a practical example.

Jul 146

Building Supervised Fine-Tuning Data from NVIDIA Open-SWE-Traces: Trajectory Parsing, Patch Analysis, Token Budgets, and Tool-Use Metrics

Learn how to load, process, and filter the NVIDIA Open-SWE-Traces dataset for supervised fine-tuning of AI models in software engineering tasks.

Jun 2662

DeepSeek lines up its first outside money: a $7bn round at up to $59bn

Learn how to fine-tune a pre-trained language model using Hugging Face's Transformers library, a technique used by AI companies like DeepSeek.

Jun 292

How to Fine-Tune LFM2 Using QLoRA and DPO: A Complete Step-by-Step Coding Tutorial on Google Colab

Learn how fine-tuning with QLoRA and DPO can make language models smarter and more useful, even on limited hardware.

Jun 2133

Adaption aims big with AutoScientist, an AI tool that helps models train themselves

Learn how to use AutoScientist, an AI tool that automates model fine-tuning for beginners. This tutorial walks you through setting up the environment, preparing data, and running automated training sessions.

May 1383