g-assismoraes/DeltaP2S-Llama2-13B-P2S-MetaMath-S13

TEXT GENERATIONPricing:Input $1.5 / Output $2.1Concurrent Unit Cost:1Model Size:13BQuant:FP8Context Size:4kPublished:Sep 1, 2026Architecture:Transformer Featherless Exclusive Cold

The g-assismoraes/DeltaP2S-Llama2-13B-P2S-MetaMath-S13 model is a 13 billion parameter language model based on the Llama 2 architecture, fine-tuned for mathematical reasoning. It was developed by g-assismoraes and specifically trained using the Delta-P2S experiment package on a MetaMath dataset. This model is optimized for solving mathematical problems and understanding complex mathematical formulas, making it suitable for applications requiring strong quantitative reasoning capabilities.

Loading preview...

Model Overview

The g-assismoraes/DeltaP2S-Llama2-13B-P2S-MetaMath-S13 is a 13 billion parameter language model built upon the Llama 2 architecture. This model has undergone specialized fine-tuning using the Delta-P2S experimental package, focusing on enhancing its mathematical reasoning abilities.

Key Capabilities

  • Mathematical Reasoning: Specifically trained on a MetaMath dataset, indicating a strong focus on mathematical problem-solving.
  • Llama 2 Base: Benefits from the robust foundation and general language understanding of the Llama 2 family.
  • Delta-P2S Fine-tuning: Utilizes a specialized training approach (Delta-P2S) for targeted performance improvements in its domain.

Good For

  • Mathematical Problem Solving: Ideal for tasks requiring the interpretation and solution of mathematical equations and problems.
  • Quantitative Analysis: Suitable for applications that involve processing and reasoning with numerical and formulaic data.
  • Research in Mathematical LLMs: Provides a specialized base for further research and development in mathematical language models.