| license: mit | |
| datasets: | |
| - weizhiwang/OpenMLLM-Data | |
| - open-thoughts/OpenThoughts-114k | |
| - HumanLLMs/Human-Like-DPO-Dataset | |
| - FreedomIntelligence/medical-o1-reasoning-SFT | |
| metrics: | |
| - accuracy | |
| - character | |
| - precision | |
| - recall | |
| - f1 | |
| - brier_score | |
| base_model: | |
| - Zyphra/Zonos-v0.1-transformer | |
| - deepseek-ai/DeepSeek-R1 | |