Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v15

TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kTool Calling:SupportedPublished:Jul 1, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v15 is a 3.1 billion parameter instruction-tuned causal language model, developed by Smilesjs. This model is finetuned from unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit, leveraging Unsloth and Huggingface's TRL library for faster training. It is designed for coding-related tasks, building upon the Qwen2.5-Coder architecture with a 32768 token context length.

Loading preview...

Smilesjs/chemsmart-qwen2.5-coder-3b-instruct-v15 Overview

This model is a 3.1 billion parameter instruction-tuned language model developed by Smilesjs. It is built upon the Qwen2.5-Coder architecture, specifically finetuned from the unsloth/Qwen2.5-Coder-3B-Instruct-bnb-4bit base model. A key aspect of its development is the utilization of Unsloth and Huggingface's TRL library, which enabled a 2x faster training process.

Key Characteristics

  • Base Model: Finetuned from Qwen2.5-Coder-3B-Instruct-bnb-4bit.
  • Parameter Count: 3.1 billion parameters, offering a balance between performance and efficiency.
  • Context Length: Supports a substantial context window of 32768 tokens, beneficial for handling longer code snippets or complex instructions.
  • Training Efficiency: Benefits from Unsloth's optimizations for accelerated training.

Intended Use Cases

Given its coder lineage and instruction-tuned nature, this model is primarily suited for:

  • Code Generation: Assisting with writing code in various programming languages.
  • Code Explanation: Providing explanations for existing code.
  • Debugging Assistance: Helping identify and suggest fixes for code errors.
  • Instruction Following: Executing complex coding-related instructions effectively.

Finetunes
2 models