pshahabinejad/qwen-coder-educational-mt

TEXT GENERATIONConcurrency Cost:2Model Size:32.8BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:Jun 4, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The pshahabinejad/qwen-coder-educational-mt is a 32.8 billion parameter Qwen2 model developed by pshahabinejad, fine-tuned from unsloth/qwen2.5-coder-32b-instruct-bnb-4bit. This model was trained using Unsloth and Huggingface's TRL library, achieving 2x faster training. It is designed for instructional purposes, leveraging its base as a coder model with a 32768 token context length.

Loading preview...

Model Overview

The pshahabinejad/qwen-coder-educational-mt is a 32.8 billion parameter Qwen2 model, developed by pshahabinejad. It is a fine-tuned version of the unsloth/qwen2.5-coder-32b-instruct-bnb-4bit base model, indicating its primary focus on coding-related tasks and instruction following.

Key Characteristics

  • Base Model: Fine-tuned from unsloth/qwen2.5-coder-32b-instruct-bnb-4bit, suggesting strong capabilities in code generation and understanding.
  • Training Efficiency: The model was trained with Unsloth and Huggingface's TRL library, resulting in a 2x faster training process compared to standard methods.
  • Context Length: Features a substantial context window of 32768 tokens, beneficial for handling longer code snippets or complex instructions.

Intended Use Cases

This model is particularly well-suited for educational applications related to coding, given its "educational-mt" designation and its foundation as a coder model. Its efficient training process and large context window make it a robust choice for tasks requiring detailed code analysis, generation, or instructional content creation within a coding context.