igarin/Qwen2.5-Coder-7B-20260302-MERGED-16bit

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Mar 2, 2026License:cc-by-nc-4.0Architecture:Transformer Open Weights Cold

The igarin/Qwen2.5-Coder-7B-20260302-MERGED-16bit is a 7.6 billion parameter Qwen2.5-Coder model, fine-tuned by igarin, designed for code-related tasks. It was trained using Unsloth and Huggingface's TRL library, enabling faster fine-tuning. This model is optimized for coding applications, leveraging its 32K context length for processing substantial codebases.

Loading preview...

Model Overview

The igarin/Qwen2.5-Coder-7B-20260302-MERGED-16bit is a 7.6 billion parameter language model, fine-tuned by igarin. It is based on the Qwen2.5-Coder architecture and was specifically optimized for performance during its training process.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/Qwen2.5-Coder-7B-Instruct-bnb-4bit.
  • Training Efficiency: Leverages Unsloth and Huggingface's TRL library, resulting in a 2x faster fine-tuning process.
  • Parameter Count: 7.6 billion parameters.
  • Context Length: Supports a context length of 32,768 tokens.

Intended Use

This model is primarily intended for code-related applications, benefiting from its Qwen2.5-Coder base and efficient fine-tuning. Its substantial context window makes it suitable for tasks requiring the processing of larger code segments.