Upload model weights to Hugging Face Hub with an OpenMDW 1.1 license and a required research warning. Check the published README and license file after uploading or updating to confirm that the required information is present.
Upload or publish model weights to the Hugging Face Hub. Use for model repositories, not dataset uploads or Hub downloads.
Review the instructions the agent will receive before you install.
Use the open-athena Hugging Face organization when the user has not specified a destination namespace. Honor an explicit destination from the user.
Upload models under the OpenMDW 1.1 license. Copy the official license text into the model repository's root LICENSE file and set license: openmdw-1.1 in the root README.md YAML metadata.
For every model upload, make sure the model repository's root README.md includes this exact text:
Research artifact. This model has not been properly tested or evaluated and is not necessarily secure. Use at your own risk in production settings.
For every model upload or update, also include this exact responsible-use paragraph in the model repository's root README.md. Preserve the research-artifact warning above; do not add duplicate copies of either paragraph:
We release our tools to the public with the intent that they are used safely, ethically, and responsibly. They are meant to contribute to the public's understanding of science, and aid in its advancement. By using this Marin model, you agree to comply with all applicable law.
Before publishing, check the local model card for both required paragraphs and the OpenMDW 1.1 license metadata. Do not upload a card that omits them.
Check the published README.md and LICENSE after uploading or updating the model to confirm that the research-artifact warning, responsible-use paragraph, OpenMDW 1.1 license metadata, and full license text are present.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Compare Zephyr changes using the same prepared dataset and matching execution settings. Analyze Finelog metrics for each processing stage to distinguish CPU efficiency, elapsed time, and peak memory changes, then report improvements, regressions, or tradeoffs.
Register Hugging Face datasets for Marin by inspecting their structure without downloading the full dataset. Identify text fields, configurations, and data splits, then add a dataset module and validate the mapping with a sample.
Turn a specified GCP access request into a reviewable Pulumi change and pull request. Select the narrowest suitable role and encrypt personal email identities, covering resource permissions and Cloud Run viewer access through IAP, an access gateway.
Add or update Pallas/Mosaic kernels, specialized computation routines for JAX. The skill covers reference implementations, output and gradient checks, public wrappers, fallback behavior, performance benchmarks, and hardware-specific tuning when requested.
Preserve old experiment scripts with a dated Git tag, a named snapshot of the code, and add comments linking related GitHub issues to the archived files and cleanup pull request.
Launch and continuously monitor a specified Zephyr pipeline on Iris when asked. It checks coordinator and worker health, tracks stage progress, identifies stalled or repeated failures, and requires explicit approval before stopping or restarting jobs.