LlamaFactory and Finetune_LLMs
Given the description of LlamaFactory as a unified and efficient fine-tuning framework for a wide range of LLMs and VLMs, and Finetune_LLMs as a repository for fine-tuning casual LLMs, these tools are **competitors**, as both offer functionality for fine-tuning large language models, but LlamaFactory presents itself as a more comprehensive and robust solution.
About LlamaFactory
hiyouga/LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Supports modular fine-tuning approaches including supervised fine-tuning, reward modeling, and reinforcement learning methods (PPO, DPO, KTO, ORPO), with optimizations like Flash Attention, quantized LoRA, and advanced optimizers (GaLore, BAdam, Muon). Provides both CLI and Gradio web interface for model training and inference, integrating with vLLM/SGLang for OpenAI-compatible API deployment.
About Finetune_LLMs
mallorbc/Finetune_LLMs
Repo for fine-tuning Casual LLMs
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work