joomhadi/ft-model-joomha-base-qwen2.5-coder-3b

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 5, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

The joomhadi/ft-model-joomha-base-qwen2.5-coder-3b is a 3.1 billion parameter Qwen2.5-Coder-3B-Instruct model, developed by joomhadi and fine-tuned for coding tasks. This model was optimized for faster training using Unsloth and Huggingface's TRL library, making it efficient for code generation and related applications. It features a 32768 token context length, suitable for handling substantial code snippets and complex programming instructions.

Loading preview...

Model Overview

The joomhadi/ft-model-joomha-base-qwen2.5-coder-3b is a 3.1 billion parameter language model, fine-tuned by joomhadi. It is based on the Qwen2.5-Coder-3B-Instruct architecture and is specifically designed for coding-related tasks. This model leverages a substantial 32768 token context length, enabling it to process and generate extensive code segments.

Key Capabilities

  • Code Generation: Optimized for generating programming code across various languages.
  • Efficient Training: Fine-tuned using Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
  • Large Context Window: Supports a 32768 token context, beneficial for understanding and completing complex coding projects or multi-file programming tasks.

Good For

  • Developers requiring a compact yet capable model for code completion and generation.
  • Applications that benefit from efficient, fine-tuned models for programming tasks.
  • Scenarios where a large context window is crucial for handling extensive codebases or detailed instructions.