hussnainzafar/qwen2.5-coder-0.5b-python-instruct-onnx

Qwen2.5-Coder-0.5B Python Instruct (ONNX)

Author: Hussnain Zafar
Fine-tuned by: Hussnain Zafar

This model is a fine-tuned version of Qwen/Qwen2.5-Coder-0.5B-Instruct, optimized for Python instruction following and exported to ONNX for efficient browser and WebAssembly inference.

Model Details

• Base model: Qwen/Qwen2.5-Coder-0.5B-Instruct
• Fine-tuning method: LoRA
• Dataset: python_code_instructions_18k_alpaca
• Task: Python code generation, instruction following
• Framework: PyTorch → ONNX
• Inference: onnxruntime / transformers.js

Training

• Trainable parameters: ~1.75%
• Hardware: GPU
• Precision: FP16
• Sequence length: 256

Usage (Browser / transformers.js)

import { pipeline } from "@huggingface/transformers";

const generator = await pipeline(
  "text-generation",
  "hussnainzafar/qwen2.5-coder-0.5b-python-instruct-onnx"
);

const result = await generator(
  "Write a Python function to check if a string is a palindrome"
);

console.log(result[0].generated_text);

Acknowledgements

• Qwen team for the base model
• Hugging Face for tooling and hosting

License

This model follows the same license as the base Qwen model.