Tag

#fine-tuning

3 articles

This AI Paper Introduces TinyLoRA, A 13-Parameter Fine-Tuning Method That Reaches 91.8 Percent GSM8K on Qwen2.5-7B

Researchers from Meta, Cornell, and CMU introduce TinyLoRA, a 13-parameter fine-tuning method that achieves 91.8% accuracy on GSM8K using Qwen2.5-7B.

Mar 2423

Unsloth AI Releases Unsloth Studio: A Local No-Code Interface For High-Performance LLM Fine-Tuning With 70% Less VRAM Usage

Learn how to use Unsloth Studio, a no-code interface for fine-tuning Large Language Models locally with 70% less VRAM usage.

Mar 1736

tools

How to Build a Stable and Efficient QLoRA Fine-Tuning Pipeline Using Unsloth for Large Language Models

A new tutorial demonstrates how to build a stable and efficient QLoRA fine-tuning pipeline using Unsloth, addressing common Colab issues and enabling resource-efficient LLM training.

Mar 388