Hugging Face
| Repository | What it is |
|---|---|
| Space: Triage Console | The same console as this site, runs in the browser |
| Dataset: Triage Agent Eval | The 5 cases, the expected behavior and the real Bedrock outputs |
Use the dataset
Section titled “Use the dataset”from datasets import load_dataset
cases = load_dataset("fernandofa42/triage-agent-eval", "cases", split="train")runs = load_dataset("fernandofa42/triage-agent-eval", "bedrock_runs", split="train")Use it to test your own model on the same cases: generate the answer from prompt and evidence, and compare it with expected. The Bedrock outputs are one sample per case, not a benchmark.
How it’s published
Section titled “How it’s published”The huggingface.yml workflow syncs from this repository, with the HF_TOKEN secret. Without the secret, the step is skipped with a warning.
Independent community project by Fernando Azevedo, AWS Community Builder. Not official AWS material, and not endorsed by AWS. AWS and related names are trademarks of Amazon.com, Inc. or its affiliates. MIT license.