Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nvidia/tao-finetune-cosmos-embed
Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning.
Passed 21 of 22 test cases with the skill, and 9 of 22 without it.
and 15 more in the full report
12 fixed9 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are switching our Cosmos-Embed1 baseline from the 224p variant to the 336p variant. Besides updating the resolution height and width to 336, what setting must be assigned to model.network.embed_dim?
| Checked | Without skill | With skill |
|---|---|---|
| Sets model.network.embed_dim to 768 for the 336p variant. | Missed | Passed |
The instructions your model reads when the skill loads.
Cosmos-Embed1 is a joint video-text embedder for text-to-video retrieval, video-to-video search, zero-shot/kNN classification, and semantic deduplication. The packaged CLI is cosmos-embed1 and supports train, evaluate, inference, and export.
Container image and per-action commands are in references/skill_info.yaml. Compact starting specs are in references/spec_template_*.yaml.
AutoML is not packaged for this model skill because there are no Cosmos-Embed schemas under schemas/. Always use the direct model skill actions for train, evaluate, inference, and export, even when a higher-level request includes automl_policy: on. Do not route Cosmos-Embed through workflow or AutoML skills until model-specific train schemas and templates are added.
Non-train actions such as evaluate, inference, export, and deploy flows stay in this model skill. The per-run automl_policy override does not change model metadata.
Use the published Cosmos-Embed container declared by references/skill_info.yaml
and resolved through versions.yaml. Do not build from the private
Cosmos-Embed1 source tree for normal skill use; build from source only when
developing the container itself.
TAO_SKILL_BANK_PATH="${TAO_SKILL_BANK_PATH:-$PWD}"
COSMOS_EMBED_IMAGE="${COSMOS_EMBED_IMAGE:-$(
python "$TAO_SKILL_BANK_PATH/scripts/resolve_tao_image.py" \
--skill-bank "$TAO_SKILL_BANK_PATH" \
--model tao-finetune-cosmos-embed \
--action train \
--format json |
python -c 'import json,sys; print(json.load(sys.stdin)["image"])'
)}"
docker pull "$COSMOS_EMBED_IMAGE"
Expected local workspace layout:
workspace/
├── data/
│ ├── msrvtt_test_1k.json
│ └── video/
│ ├── video7020.mp4
test cases passed, vs 9 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.