Freesolo: Best Model Trained on Freesolo

Train an LLM using Freesolo’s post-training platform. You are encouraged to explore the use of supervised fine-tuning, reinforcement learning, and distillation techniques to train a single or multi-turn model that fits into your project and has an interesting use case while demonstrating the latest post training techniques! All contestants will be given infinite training credits during the competition period.

Each member of the winning team will receive:

• A fully paid flight to San Francisco for a final round interview with Freesolo