NVIDIA-NeMo/Nemotron

nemotron-transcribe

Reference and routing skill for NVIDIA Nemotron 3.5 Transcribe. Use for model facts, checkpoint selection, inference constraints, and locating the canonical NeMo Speech main-stage training, fine-tuning, DFlash2, timestamp-serving, and quantization workflows;…

لغة النص الأصلي: الإنجليزية

pr-review

Review Nemotron pull requests for code correctness, instructions that match the implementation, first-user setup, and reproducible notebooks and cookbooks.

لغة النص الأصلي: الإنجليزية

nemotron-customizer-airgap

Prepare, validate, build, and use Nemotron Customizer airgap image bundles for offline clusters. Use when planning airgapped deployments, editing deploy/nemotron-customizer/airgap/airgap.yaml, selecting workflow targets, grouping step execution images, baking…

لغة النص الأصلي: الإنجليزية

nemotron-customize

Configure and chain repo-native Nemotron steps for curation, tokenizer extension, SDG/BYOB, training, conversion, optimization, and evaluation.

لغة النص الأصلي: الإنجليزية

nemotron-retrieval-recipes

Use for Nemotron embed/rerank recipes, including Nemotron 3.5 multimodal SDG, tuning, evaluation, and deployment. Not for generic retrieval.

لغة النص الأصلي: الإنجليزية

nemotron-lightning35

Reference desk for NVIDIA Nemotron 3.5 Lightning (30B-A3B), a hybrid Mamba-Transformer MoE with MTP built from Nano 3 Base by distillation from Super 3 Base, single-stage text SFT, RLVR, MTP boosting, and W4A16 NVFP4 quantization. Use when the user asks facts…

لغة النص الأصلي: الإنجليزية

nemotron-super35

Reference desk for NVIDIA Nemotron 3.5 Super (120B-A12B), covering vision-language architecture, MTP, distillation pretraining from Ultra 3 Base, Indic CPT, SFT, RLVR, specialist teachers, two-phase MOPD, MTP boosting, NVFP4 quantization, and inference. Use…

لغة النص الأصلي: الإنجليزية

nemotron-3-5-super-vl-finance-lora

Run the Nemotron-3.5 Super VL finance LoRA cookbook (NeMo Megatron-Bridge) end-to-end for the user, on one 8-GPU node or a Slurm cluster: data prep, checkpoint conversion, text+vision LoRA fine-tuning of the 120B-A12B model, merge to a Hugging Face…

لغة النص الأصلي: الإنجليزية

nemotron-3-5-lightning-text2sql-lora

Run the Nemotron-3.5 Lightning Text2SQL LoRA fine-tuning tutorial (NeMo Megatron-Bridge) end-to-end for the user on a single node: data prep, checkpoint conversion, LoRA fine-tuning of the 30B-A3B hybrid Mamba-Transformer MoE, and merging the adapter back to…

لغة النص الأصلي: الإنجليزية

nemotron-3-ultra-text2sql-lora

Run the Nemotron-3 Ultra Text2SQL LoRA fine-tuning tutorial (NeMo Megatron-Bridge) end-to-end for the user on their SLURM cluster: data prep, distributed checkpoint conversion, and packed LoRA fine-tuning of the 550B hybrid Mamba-Transformer MoE, ending at a…

لغة النص الأصلي: الإنجليزية

nemotron-ultra

Reference desk for NVIDIA Nemotron 3 Ultra (550B-A55B) — architecture, NVFP4 pretraining, SFT, MOPD (multi-teacher on-policy distillation), MTP boosting, quantization, inference. Use when the user asks facts about Ultra rather than building a pipeline.

لغة النص الأصلي: الإنجليزية

nemotron-add-model

Onboard a new model family (Nemotron or third-party) into skills/ — paper chunks, recipe summaries, context packs, and model card. Use when a contributor wants downstream skills like /nemotron-customize to be able to route to a new model.

لغة النص الأصلي: الإنجليزية

nemotron-add-pattern

Add a cross-cutting decision pattern under src/nemotron/steps/patterns/. Use when a recurring ML decision (tokenizer lock, eval bookends, LoRA-on-small-data, etc.) must be encoded so other skills can fire it during planning.

لغة النص الأصلي: الإنجليزية

nemotron-add-step

Add a new step under src/nemotron/steps/<category>/<step_id>/ — manifest (step.toml), runner glue, configs, and per-step README.md. Use when extending the catalog so /nemotron-customize can route to it.

لغة النص الأصلي: الإنجليزية

nemotron-nano3

Reference desk for Nemotron 3 Nano / Llama-Nemotron Nano 3 — architecture, training data, recipes, evaluation, quantization, deployment. Use when the user asks facts about the model rather than building a pipeline.

لغة النص الأصلي: الإنجليزية

nemotron-super3

Reference desk for NVIDIA Nemotron 3 Super — architecture, training data, recipes (pretrain/SFT/RL/eval/quantization), and deployment notes. Use when the user asks facts about Super3 rather than building a pipeline.

لغة النص الأصلي: الإنجليزية