Formulae/MITA-V1.1-7B-2-24-2025

Overview

Formulae/MITA-V1.1-7B is built for reasoning and deep thinking. It merges models designed for logical analysis, structured thought, and problem-solving. Using the SLERP merge method, it blends multiple reasoning-focused models while preserving their core strengths.

Rank	Type	Model	Average	IFEval	BBH	MATH	GPQA	MUSR	MMLU-PRO	CO₂ Cost
914	🤝	formulae/mita-v1.1-7b-2-24-2025	29.48 %	34.12 %	35.44 %	43.50 %	8.61 %	16.06 %	39.15 %	0.67 kg
1403	🤝	formulae/mita-v1.2-7b-2-24-2025	24.86 %	25.64 %	28.41 %	48.79 %	7.49 %	12.63 %	26.21 %	0.64 kg

Merge Details

• Base Model: open-thoughts/OpenThinker-7B
• Merged Models:
  • Open-Reasoner-Zero/Open-Reasoner-Zero-7B
  • open-thoughts/OpenThinker-7B
• Merge Method: SLERP (Spherical Linear Interpolation)
• Data Type: bfloat16
• Merge Parameters: V-shaped curve

What is SLERP?

SLERP (Spherical Linear Interpolation) is a technique for smoothly blending multiple models while maintaining their unique properties. Unlike simple weight averaging, SLERP preserves sharpness and structure during merging, making it effective for complex reasoning models. It was originally introduced by Ken Shoemake for quaternion interpolation in 3D rotations. In model merging, SLERP ensures a balanced mix of the component models, maintaining coherence and reducing degradation in performance.

Limitations & Risks

⚠ Misinformation – No built-in fact-checking, prone to hallucinations.
⚠ Complex Reasoning – May struggle with real-world accuracy despite logical consistency.

Usage Disclaimer

Formulae/MITA-V1.1-7B is an experimental reasoning model. It is not safe for deployment without manual oversight. Future updates will improve reliability, interpretability, and structured thought processes.

Contribute

We welcome contributions, including quantizations, fine-tuning, or improvements.

💡 Support Us: Buy Me a Coffee

📩 Contact: [email protected]

---

Future Development

This is part of the MITA series. We are working toward an MoE model that will combine multiple expert models for more adaptable reasoning and problem-solving.

Made possible with MergeKit.