Você está usando IA errado — entenda LoRA, QLoRA, RAG e Guardrails

Opa Galera, tudo certo? Lembrem-se pesquisem e entendam as coisas por conta própria Segue as fontes LoRA Hu et al., 2021 — "LoRA: Low-Rank Adaptation of Large Language Models" — https://arxiv.org/abs/2106.09685 QLoRA Dettmers et al., 2023 — "QLoRA: Efficient Finetuning of Quantized LLMs" — https://arxiv.org/abs/2305.14314 Repositório oficial (bitsandbytes/QLoRA) — https://github.com/artidoro/qlora RAG Lewis et al., 2020 — "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks" — https://arxiv.org/abs/2005.11401 Quantização (GGUF / GPTQ / AWQ) llama.cpp — formato GGUF explicado — https://apxml.com/courses/practical-l... Cast AI — "LLM Quantization Methods: GPTQ, AWQ, GGUF" — https://cast.ai/blog/demystifying-qua... Documentação Qwen sobre GGUF/AWQ — https://qwen.readthedocs.io/en/v1.5/q... Temperatura, Top-p e Top-k OpenAI Developer Community — "Temperature and top_p interactions" — https://community.openai.com/t/temper... "Understanding LLM Temperature and Other Parameters" — https://apxml.com/courses/prompt-engi... Guardrails e segurança OWASP Top 10 for LLM Applications — https://owasp.org/www-project-top-10-... Wallace et al., 2024 — "The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions" — https://arxiv.org/abs/2404.13208