2026년 7월 13일 · 11 min read · llm / paper-reading
Paper notes on Llama 2 covering its commercial license, a base model scaled to 2T tokens with 4k context and GQA, and the Llama 2-Chat alignment pipeline (SFT → two reward models → iterative RLHF with rejection sampling + PPO → GAtt). It fuses LLaMA's open base lineage with InstructGPT's RLHF at production quality.
2026년 7월 10일 · 14 min read · floci / localstack
Floci is an always-free, open-source local AWS emulator with no account, no auth token, and no feature gates. A single Quarkus + GraalVM native container emulates 68 AWS services behind one port, 4566. We analyze its Smithy-spec protocol routing, descriptor-driven service catalog, four storage modes, and real Docker execution — against LocalStack.