Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Instruction Tuning with GPT-4
| Date | Stars |
|---|---|
| 2026-07-31 | 4333 |
| 2026-08-02 | 4334 |
| 2026-08-06 | 4334 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Instruction Tuning with GPT-4
Baolin Peng*, Chunyuan Li*, Pengcheng He*, Michel Galley, Jianfeng Gao (*Equal Contribution)
[[Project Page](https://instruction-tuning-with-gpt-4.github.io/)] [[Paper](https://arxiv.org/abs/2304.03277)]
<p align="center">
<img src="https://instruction-tuning-with-gpt-4.github.io/images/gpt4llama_logo.png" width="50%"> <br>
Pronounced as "GPT-4-LLM" or "GPT-for-LLM", image is generated by <a href="https://gligen.github.io/">GLIGEN</a>
</p>
[](https://github.com/tatsu-lab/stanford_alpaca/blob/main/LICENSE)
[](https://github.com/tatsu-lab/stanford_alpaca/blob/main/DATA_LICENSE)
This is the repo for the GPT-4-LLM, which aims to share data generated by GPT-4 for building an instruction-following LLMs with supervised learning and reinforcement learning. The repo contains:
- English Instruction-Following [Data](#data-release) generated by GPT-4 using Alpaca prompts for fine-tuning LLMs.
- Chinese Instruction-Following [Data](#data-release) generated by GPT-4 using Chinese prompts translated from Alpaca by ChatGPT.
- Comparison [Data](#data-release) ranked by GPT-4 to train reward models.
- Answers on Unnatural Instructions [Data](#data-release) from GPT-4 to quantify the gap between GPT-4 and instruction-tuned models at scale.
**Usage and License Notices**: The data is intended and licensed for research use only. The dataset is CC BY NC 4.0 (allowing only non-commercial use) and models trained using the dataset should not be used outside of research purposes.
- [Overview](#overview)
- [GPT-4 Data Release](#data-release)
- [How Good is the Data?](#how-good-is-the-data)
- [Fine-tuning with the Data](#fine-tuning-with-the-data)
- [Reproduce Figure Plots](#collect-results-and-reproduce-figure-plots)
## :fire: News
<!---
* **[2023.04.07]** Data restored.
* **[2023.04.07]** :warning: We turn off the data downloading temporarily.
-->
* **[2023.04.17]** Visual instruction tuning with GPT-4 is released! Please check out the multimodal model LLaVA: [[Project Page](https://llava-vl.github.io/)] [[Paper](https://arxiv.org/abs/2304.08485)] [[Demo](https://llava.hliu.cc/)] [[Code]](https://github.com/haotian-liu/LLaVA) [[Data](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K)] [[Model](https://huggingface.co/liuhaotian/LLaVA-13b-delta-v0)]
* **[2023.04.15]** Updated comparision data, including three model responses and GPT-4 evaluation scores.
* **[2023.04.06]** Paper and data are released.
## Overview
Large Language Models (LLMs) have shown impressive generalization capabilities such as in-context-learning and chain-of-thoughts reasoning. To enable LLMs to follow natural language instructions and complete real-world tasks, researchers have been exploring methods of instruction-tuning of LLMs. To advance the state of the art of instruction-tuning for LLMs, we present the first attempt to use GPT-4 to generate instruction-following data for LLM finetuning.
## Data Release
* [`alpaca_gpt4_data.json`](./data/alpaca_gpt4_data.json) contains 52K instruction-following data generated by GPT-4 with prompts in Alpaca.
This JSON file has the same format as Alpaca data, except the output is generated by GPT-4:
- `instruction`: `str`, describes the task the model should perform. Each of the 52K instructions is unique.
- `input`: `str`, optional context or input for the task.
- `output`: `str`, the answer to the instruction as generated by `GPT-4`.
* [`alpaca_gpt4_data_zh.json`](./data/alpaca_gpt4_data_zh.json) contains 52K instruction-following data generated by GPT-4 with Alpaca prompts translated into Chinese by ChatGPT. This JSON file has the same format.
* [`comparison_data.json`](./data/comparison_data_v2.json) ranked responses from three models, including GPT-4, GPT-3.5 and OPT-IML by asking GPT-Excerpt of 7,909 characters
Read on GitHub
11
8
2
Ikko Eltociear Ashimine · Japan
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:bf1536444cf7e934, topic:instruction-tuning, desc:instruction tuning
matched fp:bf1536444cf7e934, topic:llama
matched fp:bf1536444cf7e934, topic:chatgpt