library_name: transformerslicense: apache-2.0 base_model: Qwen/Qwen2.5-1.5B-Instruct: - instruction-tuned - mathematical-reasoning - text-generation - cpu-compatible
Qwen/Qwen2.5-1.5B-Instruct Local Setup Guide
Overview
This repository, hosted by remiai3, provides free resources for students to run the Qwen/Qwen2.5-1.5B-Instruct model locally for research and experimental purposes. It includes scripts, documentation, and setup instructions, with no fees or hidden charges.
Model Details
Name:Qwen/Qwen2.5-1.5B-Instruct
Organization: Qwen (Alibaba Cloud)
Attributes:
2.5 billion parameters
Instruction-tuned for mathematical reasoning and text generation
Supports float16 precision for CPU efficiency
License: Apache-2.0
Original Repository: Qwen/Qwen2.5-1.5B-Instruct
Setup
Clone this repository: git clone
https://huggingface.co/remiai3
Install dependencies: pip install -r requirements.txt
Download model weights from the original repository using your Hugging Face token.
Run the provided scripts to download and test the model.
Requirements
Python 3.10.9 (must needed)
Minimum 16GB RAM (24GB recommended for finetuning)
~5GB disk space for model weights
Internet connection for downloading weights
Usage
Use download_model.py to download the model weights.
Run test_model.py for inference (e.g., solving math problems).
Optionally, use app.py for a web-based interface.
Refer to documents.txt for detailed instructions.
License
This repository is free for student use. The model weights are licensed under Apache-2.0 by Qwen. See the original repository for details.
Contact
Open a discussion on the remiai3 repository for support or questions.
