https://github.com/soran-ghaderi/nir_code_release

Neural Integration of Iterative Reasoning (NIR) in LLMs for Code Generation
https://github.com/soran-ghaderi/nir_code_release

code-generation llm reasoning

Last synced: about 2 months ago
JSON representation

Neural Integration of Iterative Reasoning (NIR) in LLMs for Code Generation

• Host: GitHub
• URL: https://github.com/soran-ghaderi/nir_code_release
• Owner: soran-ghaderi
• License: mit
• Created: 2024-07-13T01:49:27.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-01-06T17:19:01.000Z (9 months ago)
• Last Synced: 2025-02-22T01:24:14.628Z (8 months ago)
• Topics: code-generation, llm, reasoning
• Language: Python
• Homepage: https://soran-ghaderi.github.io/nir/
• Size: 6.47 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Neural Integration of Iterative Reasoning (NIR) in LLMs for Code Generation

Pytorch implementation for NIR.


    

        

            

        

        

            
Neural Integration of Iterative Reasoning (NIR)

            


                


Project Website: Official Site



                


Author Website: Soran Ghaderi



                


Email: soran.ghaderi.ac@gmail.com

                


University: University of Essex

                


Year: 2024

            

        

    


## Citation

```bibtex

@mastersthesis{soran_2024_essex,

  title        = {Neural Integration of Iterative Reasoning (NIR) in LLMs for Code Generation},

  author       = {Ghaderi, Soran},

  year         = 2024,

  school       = {University of Essex},

  type         = {Master's thesis},

  doi          = {https://doi.org/10.13140/RG.2.2.18855.25769}

}

```

## Prerequisites & Dependencies & Running the Codes

**Note:** Ensure dependencies are installed before running.

```bash

# Create virtual environment

python -m venv venv

source venv/bin/activate

# Install dependencies

pip install -r requirements.txt

```

**Important:** To use the Llama 3.1 model, you'll need a token:

1. Create a HuggingFace account

2. Request an access token

3. Use the token in the notebooks and *.py files

### Notebooks (Recommended)

Run notebooks in order:

1. `preprocess_dataset.ipynb`

2. `evaluation.ipynb`

3. `analysis.ipynb`

### Python Scripts (Alternative)

Run scripts in sequence:

1. `preprocess_dataset.py`

2. `final_evals.py`

3. `analysis.py`

**Experimental implementations:** Please note that none of the experimental implementations are included in the evaluations

nor in the dissertation report. They also need minor changes and further modification to be actually useful.

Memory manager, using CRV retrieval, 

similarity-based retrieval, a differential neural computers adaptation.