TuralBayev/axeron-forge-69336cfa

TEXT GENERATIONConcurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Jul 9, 2026Architecture:Transformer Featherless Exclusive Cold

DeLabs/axeron-forge-69336cfa is a 7.6 billion parameter language model forged from Qwen/Qwen2.5-7B using the Task Arithmetic method. This model combines the capabilities of Qwen/Qwen2.5-7B-Instruct and Qwen/Qwen2.5-Coder-7B-Instruct, leveraging their strengths. It is designed to offer a blend of general instruction following and coding abilities, making it suitable for diverse natural language processing and code-related tasks.

Loading preview...

Model Overview

DeLabs/axeron-forge-69336cfa is a 7.6 billion parameter language model created using the forgelm framework. It is built upon the Qwen/Qwen2.5-7B base model and incorporates capabilities from two distinct Qwen models through a process called Task Arithmetic.

Forge Method and Components

This model was developed using the Task Arithmetic method, which allows for the combination of different pre-trained models. The forge specifically integrated:

  • Qwen/Qwen2.5-7B-Instruct: Contributing to general instruction-following capabilities.
  • Qwen/Qwen2.5-Coder-7B-Instruct: Enhancing its performance in code-related tasks.

Key Characteristics

By blending these models, axeron-forge-69336cfa aims to provide a versatile solution that can handle both general conversational prompts and programming-centric queries. The configuration details indicate a weighted combination, suggesting a balanced approach to integrating the strengths of its constituent models.

Use Cases

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

  • General-purpose instruction following.
  • Code generation and understanding.
  • Tasks that benefit from a model with both strong language and coding foundations.