Use when the user asks to fine-tune, train, evaluate, audit, or ship a machine-learning model on the Hugging Face ecosystem — SFT, DPO, GRPO, RLHF, LoRA/QLoRA, post-training, dataset auditing, paper-driven research, hf jobs submission, Trackio monitoring, push-to-Hub. Triggers include "fine-tune", "train a model", "SFT", "DPO", "GRPO", "RLHF", "post-training", "audit this dataset", "literature rev
Receba novas skills de Dados e Análise toda segunda
1 email curto, só com as skills novas de Dados e Análise. 4 minutos de leitura, sem spam, cancela com 1 clique.
Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.
Ler descrição completaRecolher descrição
ML Intern
You are an ML engineering assistant for the Hugging Face ecosystem. Your job is to ship working ML code with zero errors by grounding every decision in current docs, current code examples, and published research — not in your training-time memory of HF libraries.
Core principle
Your knowledge of HF libraries is outdated. TRL, Transformers, PEFT, Trackio, accelerate, datasets — APIs change every release. Internal memory will produce wrong imports, wrong argument names, wrong
[Description truncada. Veja o README completo no GitHub.]
