📚 Jackrong LLM Fine-Tuning Guide: A guide to fine-tuning LLMs
A large-scale knowledge base for fine-tuning large language models has been released. The repository includes recipes for SFT, GRPO, and GSPO, as well as tools for data preparation and working with Qwen and Llama 3.2 models.
🌍 The project provides standardized pipelines, lowering the barrier to entry for developers.
👤 You can use ready-made scripts and notebooks for Google Colab and Kaggle.
Source 1: https://github.com/R6410418/Jackrong-llm-finetuning-guide