BrainWave-ML/SmolLM2-1.7b-maths-orpo

Uploaded model

• Developed by: BrainWave-ML
• License: apache-2.0
• Finetuned from model : HuggingFaceTB/SmolLM2-1.7B-Instruct

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.