Dasko2-0/qwen2.5-coder-3b-mentor

TEXT GENERATIONPricing:Input $0.32 / Cached $0.064 / Output $1.6Concurrent Unit Cost:1Model Size:3.1BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Aug 24, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

Dasko2-0/qwen2.5-coder-3b-mentor is a 3.1 billion parameter Qwen2.5-based causal language model developed by Dasko2-0. This model is finetuned from unsloth/qwen2.5-coder-3b-instruct-bnb-4bit and optimized for coding tasks. It leverages Unsloth and Huggingface's TRL library for efficient training, making it suitable for code generation and programming-related applications.

Loading preview...

Model Overview

Dasko2-0/qwen2.5-coder-3b-mentor is a 3.1 billion parameter language model developed by Dasko2-0. It is built upon the Qwen2.5 architecture and specifically finetuned for coding applications. This model was trained using Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.

Key Capabilities

  • Code Generation: Optimized for generating programming code.
  • Instruction Following: Inherits instruction-following capabilities from its base model, unsloth/qwen2.5-coder-3b-instruct-bnb-4bit.
  • Efficient Training: Benefits from Unsloth's optimizations for faster finetuning.

Good For

  • Developers seeking a compact yet capable model for code-related tasks.
  • Applications requiring efficient code generation or understanding.
  • Environments where faster training and deployment of coding models are beneficial.