Menu
O SkillsMP coletou 8 skills de OpenRaiser/NanoResearch. Abra uma skill para revisar a origem e os detalhes.
Mostrando 8 de 8 skills coletadas.
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace,…
Idioma do texto original: inglês
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's…
Idioma do texto original: inglês
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
Idioma do texto original: inglês
Search academic literature and generate research hypotheses
Idioma do texto original: inglês
Produce an experiment blueprint from a research hypothesis
Idioma do texto original: inglês
Draft a LaTeX research paper from all previous stage outputs
Idioma do texto original: inglês
Write publication-ready ML/AI/Systems papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM, OSDI, NSDI, ASPLOS, SOSP. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX…
Idioma do texto original: inglês
Generate a Python code skeleton from an experiment blueprint
Idioma do texto original: inglês