A LoRA SFT of Qwen2.5-7B-Instruct, fine-tuned to be a direct, opinionated pairing partner for ML/AI engineering work: debugging training runs, reasoning about architecture choices, catching common infra mistakes, and designing evals. Built as a local red-team sounding board for our own lab’s work — sanity-checking experiment design, spotting confounds, reviewing training scripts before launch. Trained on DuoNeural/ml-ai-engineer-sft, a synthetic dataset spanning 48 topics (PyTorch debugging, distributed training, RLHF/GRPO, quantization, architecture critique, MLOps, infra) at three difficulty tiers and five response styles. The base Qwen2.5-7B-Instruct is fluent and thorough, but tends toward exhaustive, hedging checklists that enumerate every possibility without committing to the most likely root cause. The SFT model leads with a diagnosis first, then the fix — closer to how an experienced engineer actually responds to a bug report. Example — Mixture-of-Experts failure mode («8 experts, top-2 routing, no auxiliary load-balancing loss, training on a 2B token corpus. What’s the most likely failure mode?») > Base: «Several potential failure modes can arise… 1. Overfitting… > 2.…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: DuoNeural
Теги: qwen2, ml-engineering, sft, lora, qwen2.5, debugging, conversational, en
Лайков: 3 | Загрузок: 15
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
