tao-finetune-cosmos-reason

Cosmos-RL Supervised fine-tuning (SFT) of Cosmos Reason video QA models. The packaged default base model is hf_model://nvidia/Cosmos3-Nano . Pretrained weights are sourced from HuggingFace, not NGC. Gated HuggingFace models require HF_TOKEN . Some Cosmos-RL images cannot load the native Cosmos3 Omni checkpoint format directly; for those images, convert Cosmos3-Nano to a Qwen3-VL HF safetensors directory before train/evaluate and use that converted directory as the PTM path. Uses FSDP-based parallelism with dp_shard_size for GPU count and dp_replicate_size for node count (not the standard num_gpus / num_nodes ). Requests for "Cosmos Reason 3", "Cosmos3 Nano Reasoner", or nvidia/Cosmos3-Nano are handled by this skill. There is no separate Cosmos3 model directory in the skill bank; route those requests here. Override the base HuggingFace model only when the user explicitly asks for a different model. Deep detail lives in references; load the smallest one that matches the task: Show more Installs 579 Repository nvidia/skills GitHub Stars 1.9K First Seen Jun 8, 2026 Security Audits Gen Agent Trust Hub Pass Socket Warn Snyk Warn