AI & LLM Engineering · By wshobson

Reference for designing and tuning production LLM prompts: few-shot examples, chain-of-thought, structured outputs, templates and system prompts.

wshobson/agents

Plans memory headroom, works through out-of-memory failures and watches temperature and power during long ML training jobs on NVIDIA DGX Spark.

wshobson/agents

Preflight checks and diagnosis for ten known failure modes of ML training on NVIDIA DGX Spark's GB10, spanning launch errors, memory, thermals, bandwidth and precision.

wshobson/agents

Helps choose and tune embedding models for semantic search and RAG: model comparison, chunking, preprocessing, normalization and caching.

wshobson/agents

Covers distance metrics, index types and tuning for similarity search on vector databases, from semantic search to RAG retrieval.

wshobson/agents

Shows how to run vector and keyword search side by side and merge their results, so retrieval catches both meaning and exact terms in RAG and search systems.

wshobson/agents

Build retrieval-augmented generation systems: pick a vector database and embedding model, choose retrieval and reranking strategies, and start from a LangGraph pipeline.

wshobson/agents

Tune vector indexes for latency, recall and memory: pick an index type by data size, adjust HNSW parameters and choose a quantization level.

wshobson/agents

Prepare, format, and validate datasets for supervised fine-tuning and preference training.

wshobson/agents

Build the evaluation harness that gates every fine-tuning run — golden sets, per-failure-mode graders, judge calibration, and base-model baselines.

wshobson/agents

Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model.

wshobson/agents

Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR).

wshobson/agents

Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration.

wshobson/agents

Configure LoRA and QLoRA supervised fine-tuning with current best-practice hyperparameters.

wshobson/agents

Align a fine-tuned model with preference data using DPO, ORPO, KTO, or SimPO.

wshobson/agents

Python resource management with context managers, cleanup patterns, and streaming.

wshobson/agents

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13).

wshobson/agents

Convert evaluation traces and production logs into SFT examples and preference pairs.

wshobson/agents

Fine-tune vision-language models (VLMs) with supervised learning on image+text data.

wshobson/agents

Export a promoted fine-tuned model in the right deployment format — merged safetensors, LoRA-only, GGUF with imatrix, or FP8.

wshobson/agents

Design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced X For You algorithm.

wshobson/agents