RunRL
Python client for interacting with the RunRL API, providing tools for training and deploying machine learning models.
Installation
Learn how to install and set up the RunRL client.
API Reference
Explore the complete API documentation.
Examples
See practical examples of using RunRL.
Troubleshooting
Find solutions to common issues.
Quick Start
from runrl import RunRL
# Initialize with your API key
client = RunRL(api_key="rl-your-api-key")
# Upload prompt and reward files
prompt_file = client.upload_prompt_file("path/to/prompt.jsonl", "My Prompt File")
reward_file = client.upload_reward_file("path/to/reward.jsonl", "My Reward File")
# Launch a training run
run = client.create_run(
model_name="Qwen/Qwen3-4B",
prompt_file=prompt_file['id'],
reward_file=reward_file['id'],
epochs=2,
learning_rate=2e-6
)
print(f"Created run with ID: {run['id']}")