itsmostafa

Carrega e utiliza modelos pré-treinados com Hugging Face Transformers. Ideal para trabalhar com modelos do Hub, executar inferência com a API Pipeline, ajustar modelos com o Trainer, ou lidar com tarefas de texto, visão, áudio e multimodais.

Memory-efficient fine-tuning with 4-bit quantization and LoRA adapters. Use when fine-tuning large models (7B+) on consumer GPUs, when VRAM is limited, or when standard LoRA still exceeds memory. Builds on the lora skill.

Patterns and architectures for building AI agents and workflows with LLMs. Use when designing systems that involve tool use, multi-step reasoning, autonomous decision-making, or orchestration of LLM-driven tasks.