Alelcv27/Llama3.1-8B-Arcee-Math-Code-v1

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:Apr 2, 2026Architecture:Transformer Cold

Alelcv27/Llama3.1-8B-Arcee-Math-Code-v1 is an 8 billion parameter language model based on the Llama 3.1 architecture, created by Alelcv27 using the Arcee Fusion merge method. This model specifically combines capabilities from a Llama3.1-8B-Math-v3 base with a Llama3.1-8B-Code model. It is designed to excel in both mathematical reasoning and code generation tasks, offering a specialized solution for developers requiring proficiency in these domains.

Loading preview...

Model Overview

Alelcv27/Llama3.1-8B-Arcee-Math-Code-v1 is an 8 billion parameter language model built upon the Llama 3.1 architecture. It was developed by Alelcv27 through a specialized merging process using mergekit and the Arcee Fusion method.

Key Capabilities

This model is a fusion of two distinct Llama 3.1-8B variants:

  • Mathematical Reasoning: It incorporates capabilities from Alelcv27/Llama3.1-8B-Math-v3, suggesting enhanced performance in mathematical problem-solving and logical reasoning tasks.
  • Code Generation: By integrating Alelcv27/Llama3.1-8B-Code, the model is equipped for proficient code generation across various programming languages.

Merge Details

The Arcee Fusion merge method was applied, using Alelcv27/Llama3.1-8B-Math-v3 as the base model. The merge configuration specifically combined layers from both the math-optimized and code-optimized Llama 3.1-8B models, aiming to create a synergistic model proficient in both domains.

Ideal Use Cases

This model is particularly well-suited for applications requiring a strong combination of:

  • Technical Problem Solving: Tasks involving complex mathematical equations, algorithms, or logical puzzles.
  • Software Development: Generating, debugging, or understanding code snippets and programming logic.