https://github.com/iaar-shanghai/grimoire
Grimoire is All You Need for Enhancing Large Language Models
https://github.com/iaar-shanghai/grimoire
baichuan chatgpt datasets gpt-4 grimoire icl in-context-learning llama llm phi2
Last synced: about 1 year ago
JSON representation
Grimoire is All You Need for Enhancing Large Language Models
- Host: GitHub
- URL: https://github.com/iaar-shanghai/grimoire
- Owner: IAAR-Shanghai
- License: apache-2.0
- Created: 2024-01-09T02:33:41.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2024-02-29T05:44:07.000Z (over 2 years ago)
- Last Synced: 2025-06-02T08:44:47.614Z (about 1 year ago)
- Topics: baichuan, chatgpt, datasets, gpt-4, grimoire, icl, in-context-learning, llama, llm, phi2
- Language: Python
- Homepage: https://arxiv.org/abs/2401.03385
- Size: 3.61 MB
- Stars: 115
- Watchers: 6
- Forks: 13
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Citation: CITATION.bib
Awesome Lists containing this project
README
[English](./README.md) | [ไธญๆ็ฎไฝ](./README.zh_CN.md)
๐ Grimoire is All You Need for Enhancing LLMs
๐กEnhance the capabilities of small language models using grimoires.
## Contents
- [Introduction](#introduction)
- [Project Structure](#project-structure)
- [Get Started](#get-started)
- [Results](#results)
- [Contact Us](#contact-us)
- [TODOs](#TODOs)
- [Citation](#citation)
## Introduction
In-context learning (ICL) is one of the key methods for enhancing the performance of large language models on specific tasks by providing a set of few-shot question and answer examples. However, the ICL capability of different types of models shows significant variation due to factors such as model architecture, volume of learning data, and the size of parameters. Generally, the larger the model's parameter size and the more extensive the learning data, the stronger its ICL capability. In this paper, we propose a method SLEICL (Strong LLM Enhanced ICL) that `involves learning from examples using strong language models and then summarizing and transferring these learned skills to weak language models for inference and application.`
This ensures the stability and effectiveness of ICL. Compared to directly enabling weak language models to learn from prompt examples, SLEICL reduces the difficulty of ICL for these models. Our experiments, conducted on up to eight datasets with five language models, demonstrate that weak language models achieve consistent improvement over their own zero-shot or few-shot capabilities using the SLEICL method. Some weak language models even surpass the performance of GPT4-1106-preview (zero-shot) with the aid of SLEICL.
## Project Structure
The project is organized into several key directories and modules. Here's an overview of the project structure:
```
.
โโโ archived # Store the grimoire and hard samples used in our experiment.
โโโ assets # Store project assets, such as images, diagrams, or any visual elements used to enhance the presentation and understanding of the project.
โโโ configs # Store configuration files.
โโโ core # Core codebase.
โ โโโ data # Data processing module.
โ โโโ evaluator # Evaluator module.
โ โโโ llm # Load Large Language Models (LLMs) module.
โโโ data # Store datasets and data processing scripts.
โโโ external # Store the Grimoire Ranking model based on the classifier approach.
โโโ outputs # Store experiment output files.
โโโ prompts # Store text files used as prompts when interacting with LLMs.
โโโ stats # Store experiment statistical results.
โโโ tests # Store test code or unit tests.
```
## Get Started
1. Clone the repository.
* `git clone https://github.com/IAAR-Shanghai/Grimoire.git && cd Grimoire`
2. Prepare for the conda environment.
* `conda create -n grimoire python=3.8.18`
* `conda activate grimoire`
3. Install Python dependencies and process the data.
* `chmod +x setup.sh`
* `./setup.sh`
4. Configure
* the llms in [configs/llm.yaml](configs/llm.yaml).
* the experiments in [configs/experiment.yaml](configs/experiment.yaml).
* If it is necessary to reproduce our experiment, you can load the grimoire and hard samples used in this experiment to the current path using the following command: `cp -r ./archived/.cache ./`.
5. Look into [experiments.py](experiments.py) to see how to run experiments.
6. Run [analyst.py](analyst.py) to analyze the results saved in `outputs`.
**Note:** Regarding the deployment of LLMs, we also provide some reference [tutorials](./vllm.md).
## Results
## Contact Us
For any questions, feedback, or suggestions, please open a GitHub Issue. You can reach out through [GitHub Issues](https://github.com/IAAR-Shanghai/Grimoire/issues).
## TODOs
Click me to show all TODOs
- [x] Write a unified `setup.sh` to implement Python dependencies installation and the implementation of `embed.py` and `compute_similarity.py`;
- [x] Provides a simple tutorial on deploying vllm models;
- [x] Load large models directly from `huggingface`;
- [ ] Add configurable items in `experiment.yaml`;
- [ ] The experimental environment and code are packaged based on Docker, which is convenient for researchers to use and deploy quickly;
## Citation
```
@article{Grimoire,
title={Grimoire is All You Need for Enhancing Large Language Models},
author={Ding Chen and Shichao Song and Qingchen Yu and Zhiyu Li and Wenjin Wang and Feiyu Xiong and Bo Tang},
journal={arXiv preprint arXiv:2401.03385},
year={2024},
}
```