Language-model engineering
Practical guides to fine-tuning, deployment, tool use and retrieval.
Reading order
- Choosing between LoRA, QLoRA and full fine-tuning
- FP16, INT8 or 4-bit? Throughput, accuracy and memory in deployment
- Serving language models under load: monitoring, rate limits and recovery
- Function calling, tool use and agent frameworks
- How RAG fills knowledge gaps: retrieval, chunking, reranking and generation