Cre4T3Tiv3/unsloth-llama3-alpaca-lora

Custom model training using modern architectures. 4-bit QLoRA fine-tuning pipeline for LLaMA 3 8B with production-grade optimization. Memory-efficient training on consumer GPUs. Published adapter on HuggingFace. From training pipeline to deployed model.

语言：Jupyter Notebook · GitHub 星标：39 · Fork：1

话题：4bit · alpaca · colab · finetuning · gradio · huggingface · instruction-tuning · llama3

在 GitHub 上查看原仓库