Cosmos-RL

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:

• references/cosmos-reason-launch.md — launch intake, preflight, per-action dataset requirements, spec construction, typical overrides.
• references/cosmos-reason-evaluate.md — evaluate (flat TOML, task types, LoRA eval, selective download, results) and datasets.
• references/cosmos-reason-automl.md — AutoML/HPO policy and search-space guidance.
• references/cosmos-reason-parameters.md — important parameters, hardware, error patterns, DEFT/gap analysis, parent-model inference mappings.

Dataclass Schemas

Generated TAO Core schemas are packaged in schemas/<action>.schema.json, with schemas/manifest.json listing available actions. Each generated schema also emits references/spec_template_<action>.yaml from the schema top-level default field. AutoML enablement is declared at the model layer in references/skill_info.yaml via automl_enabled. Runnable AutoML still requires schemas/train.schema.json and references/spec_template_train.yaml to exist and parse. Use the packaged train schema for automl_default_parameters, automl_disabled_parameters, defaults, min/max bounds, enums, option weights, math conditions, dependencies, and popular parameters. Do not expect ~/tao-core at runtime; maintainers regenerate schemas/templates before packaging the skill bank.

Train Action Policy

This model is AutoML-enabled at the model layer. Before handling any train-stage request, read references/skill_info.yaml and resolve the run override from either an explicit automl_policy value or the user's workflow request. Use automl_policy: on by default and only expose on / off in new launch prompts. Treat phrases like "turn off AutoML", "disable AutoML", "no HPO", or "plain training" as automl_policy: off for this run only. When automl_policy: on, automl_enabled: true, and both schemas/train.schema.json and references/spec_template_train.yaml are packaged, route the train action through tao-skill-bank:tao-run-automl by default with this model's skill_dir. Preserve workflow/application overrides for datasets, specs, output directories, GPU/platform settings, parent checkpoints, and automl_policy. Use direct model training only when automl_policy: off or the packaged train schema/template is missing; in the missing-schema case, report that AutoML is enabled but not runnable for this model until schemas are generated.

Non-train actions such as evaluate, inference, and quantize stay in this model skill. The per-run automl_policy override does not change model metadata.

Credentials

• HF_TOKEN (required for gated models): HuggingFace access token. For the packaged default, the user must accept the model agreement at https://huggingface.co/nvidia/Cosmos3-Nano and provide a token with read access. If the user explicitly overrides the base model, they must accept