QLoRA 기반 7B LLM 튜닝 및 14GB 모델 배포의 인프라 제약 분석
Fine-tuned 7B LLM as a broke student. And Can't even use it 😭.
Fine-tuned 7B LLM as a broke student. And Can't even use it 😭.
OptiLearn - Powered by Google Gemma 4
Cell-to-Sentence (C2S): LLM-Powered scRNA-seq Annotation with Gemma 4
Fine-Tuning Gemma 4 for Function Calling with TRL's New Multimodal Tool Support
Untangling 40-Year-Old COBOL Monoliths with Gemma 4 (Yes, Completely Offline)
I fine-tuned a bias judge for $30. The training was the easy part.
"OncoAgent: A Dual-Tier Multi-Agent Framework for Privacy-Preserving Oncology Clinical Decision Support"
Why Your Gemma 4 Fine-Tuning is Failing (and How to Fix It)
🔥 Fine-Tuning Gemma 4 on Your Own Dataset: A Step-by-Step Guide
Desktop app to generate LLM fine-tuning datasets — got +16pp on HumanEval
Growing void between enterprise and frontier AI puts open weights models in the spotlight
I built a local AI coding system that actually understands your codebase — here's what I learned
(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware
SmolVLM - small yet mighty Vision Language Model
Fine-Tuning Gemma Models in Hugging Face
Make LLM Fine-tuning 2x faster with Unsloth and 🤗 TRL
Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA