olas-prediction-leaderboard / tabs /howto_benchmark.py
arshy's picture
fix submodule
6bec1f5
raw
history blame
723 Bytes
how_to_run = """\
## Create a new Tool
- Fork the repo [here](https://github.com/valory-xyz/mech).
- Create your tool in mech/packages/{your-name-here}/f'{your-tool}.py'
- Submit a PR
## Test your Tool on the Benchmark On HF
- Navigate to the "🔥 Run the Benchmark" page
- Choose your tool and model
- Enter your API key
- Press "Run Benchmark"
- Inspect the results
## Test your Tool on the Benchmark locally
- Fork the repo [here](https://github.com/valory-xyz/olas-predict-benchmark).
- Follow the instructions in the readme.
## Run a Prediction Agent that uses these Tools to place real bets
- Fork the repo [here](https://github.com/valory-xyz/trader-quickstart).
- Follow the instructions in the readme.
"""