FreeSkills
Commits, branches and sync with the but CLI
- 361361 downloads
- 198198 likes
- 103103 saves
Works with
- Claude Code
- Codex
- Cursor
- and 3 more
Pretrain an NVDINOv2 backbone v1.0.0
Use this resource to pretrain a vision transformer backbone without labels with TAO
New
- 567 downloads
- 155 likes
- 110 saves
Free
Install with the CLI
In a terminal, from the folder you want:
npx --yes palatekit@latest install self-supervised-vit-pretraining-taoWith no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.
First time: connect the CLI with
npx --yes palatekit@latest loginThe agent writes the training spec, runs teacher-student self-distillation, then exports or distils the resulting backbone and checks its inference. It also explains the TensorRT conversion.
Mostly picked by
Updated November 2, 2026
Previews
Details
- Install guides
- Generates with
- Your agent's model
- Licence
- Apache-2.0
Similar resources
View all- Free
FreeSkills
Sentry CLI guide
- 525525 downloads
- 117117 likes
- 128128 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Drizzle ORM best practices with PostgreSQL
- 407407 downloads
- 194194 likes
- 151151 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
SLO design wizard
- 537537 downloads
- 105105 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
User stories and sprint fit
- 451451 downloads
- 150150 likes
- 132132 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Capacity-based sprint plan
- 423423 downloads
- 192192 likes
- 102102 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Startup CTO advisor
- 580580 downloads
- 201201 likes
- 242242 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
FreeSkills
Creating GitHub pull requests with quality checks
- 427427 downloads
- 230230 likes
- 196196 saves
Works with- Claude Code
- Codex
- Cursor
- and 3 more
What you get
- SKILL.md : actions, requirements and common errors
- references/spec_template_train.yaml : training spec template
- references/tao-deploy-nvdinov2.md : TensorRT deployment
Good fit for
- You want general visual features without labels
- You want a backbone for a downstream detector
Not for
Tags
- nvdinov2
- self-supervised
- vision transformer
- tao
- backbone
About
You say
“Pretrain a ViT backbone on my unlabelled images with TAO.”
Skill published by nvidia under the Apache-2.0 license, delivered in its original version.
Show moreShow less
How to use it
- Install the skill in your agent's skills folder
- Ask your agent to pretrain a vision transformer backbone without labels with TAO
- Review and adjust the result
Content preview
Files
- BENCHMARK.md7.1 KB
- config/skillspector-baseline.yaml0.8 KB
- evals/evals.json0.8 KB
- LICENSE11.3 KB
- NOTICE-PALATEKIT.md0.5 KB
- references/skill_info.yaml3 KB
- references/spec_template_deploy_gen_trt_engine.yaml0.5 KB
- references/spec_template_distill.yaml2.2 KB
- references/spec_template_export.yaml2.4 KB
- references/spec_template_inference.yaml2.3 KB
- references/spec_template_train.yaml2.2 KB
- references/tao-deploy-nvdinov2.md4 KB
- references/tao-deploy-nvdinov2.skill_info.yaml1.6 KB
- schemas/distill.schema.json41.3 KB
- schemas/export.schema.json44.1 KB
- schemas/inference.schema.json44.3 KB
- schemas/manifest.json12.7 KB
- schemas/train.schema.json41.3 KB
- skill-card.md4.2 KB
- SKILL.md12.3 KB
- skill.oms.sig7.9 KB
Origin and licence
Listed unmodified
- Author
- nvidia
- Source
- github.com/nvidia/skills/tree/ca116d60beafe1b4459f0ab790b7b450912c56b0/skills/tao-train-nvdinov2
- Licence
- Apache-2.0
Notice
« tao-train-nvdinov2 » (nvidia, Apache-2.0) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.
User reviews
–
No ratings yet
Loading reviews…