Airoboros-13B Open-source Language Model - A Synthetic Data Fine-tuned Model for Research

Airoboros 13b

Developed by jondurbin

This is a 13-billion-parameter language model based on the LlaMa architecture, fine-tuned using synthetic data, primarily for research purposes.

Large Language Model

Transformers

#Research-specific model #Synthetic data training #Jailbreak prompt validation

Downloads 229

Release Time : 5/19/2023

Model Overview

This model is an experimental 13-billion-parameter language model, fine-tuned entirely with synthetic data generated by airoboros, aimed at validating the impact of 'jailbreak' prompts on the scope of data generation.

Model Features

Synthetic data training

Fine-tuned entirely with synthetic data generated by airoboros

Research-oriented

Primarily used to validate the impact of 'jailbreak' prompts on the scope of data generation

Performance

Outperforms several comparable 13B models in GPT-4 evaluations

Model Capabilities

Text generation

Dialogue systems

Instruction following

Use Cases

Research

Language model alignment research

Investigating the impact of jailbreak prompts on model behavior

Confirmed that jailbreak prompts can generate a broader range of data

🚀 Fine-tuned 13B Parameter LlaMa Model

This is a fine-tuned 13B parameter LlaMa model, leveraging completely synthetic training data from https://github.com/jondurbin/airoboros. However, it's not recommended for use due to sub - optimal outputs and potential "harmful" data from jailbreak.

🚀 Quick Start

There's no specific quick start guide provided in the original document.

✨ Features

There's no clear feature description in the original document.

📦 Installation

There are no installation steps in the original document.

💻 Usage Examples

There are no code usage examples in the original document.

📚 Documentation

Overview

This is a fine-tuned 13b parameter LlaMa model, using completely synthetic training data created by https://github.com/jondurbin/airoboros.

⚠️ Important Note

I don't recommend using this model! The outputs aren't particularly great, and it may contain "harmful" data due to jailbreak. Please see one of the updated airoboros models for a much better experience.

Eval (gpt4 judging)

chart

Model	Raw Score	GPT - 3.5 Adjusted Score
airoboros-13b	17947	98.087
gpt35	18297	100.0
gpt4-x-alpasta-30b	15612	85.33
manticore-13b	15856	86.66
vicuna-13b-1.1	16306	89.12
wizard-vicuna-13b-uncensored	16287	89.01

Individual question scores, with shareGPT links (200 prompts generated by gpt - 4)

wb-13b-u is Wizard-Vicuna-13b-Uncensored

airoboros-13b	gpt35	gpt4-x-alpasta-30b	manticore-13b	vicuna-13b-1.1	wv-13b-u	Link
80	95	70	90	85	60	eval
20	95	40	30	90	80	eval
100	100	100	95	95	100	eval
90	100	85	60	95	100	eval
95	90	80	85	95	75	eval
100	95	90	95	98	92	eval
50	100	80	95	60	55	eval
70	90	80	60	85	40	eval
100	95	50	85	40	60	eval
85	60	55	65	50	70	eval
95	100	85	90	60	75	eval
100	95	70	80	50	85	eval
100	95	80	70	60	90	eval
95	100	70	85	90	90	eval
80	95	90	60	30	85	eval
60	95	0	75	50	40	eval
100	95	90	98	95	95	eval
60	85	40	50	20	0	eval
100	90	85	95	95	80	eval
100	95	100	95	90	95	eval
95	90	96	80	92	88	eval
95	92	90	93	89	91	eval
95	93	90	94	96	92	eval
95	90	93	88	92	85	eval
95	90	85	96	88	92	eval
95	95	90	93	92	91	eval
95	98	80	97	99	96	eval
95	93	90	87	92	89	eval
90	85	95	80	92	75	eval
90	85	95	93	80	92	eval
95	92	90	91	93	89	eval
100	95	90	85	80	95	eval
95	97	93	92	96	94	eval
95	93	94	90	88	92	eval
90	95	98	85	96	92	eval
90	88	85	80	82	84	eval
90	95	85	87	92	88	eval
95	97	96	90	93	92	eval
95	93	92	90	89	91	eval
90	95	93	92	94	91	eval
90	85	95	80	88	75	eval
85	90	95	88	92	80	eval
90	95	92	85	80	87	eval
85	90	95	80	88	75	eval
85	80	75	90	70	82	eval
90	85	95	92	93	80	eval
90	95	75	85	80	70	eval
85	90	80	88	82	83	eval
85	90	95	92	88	80	eval
85	90	80	75	95	88	eval
85	90	80	88	84	92	eval
80	90	75	85	70	95	eval
90	88	85	80	92	83	eval
85	75	90	80	78	88	eval
85	90	80	82	75	88	eval
90	85	40	95	80	88	eval
85	95	90	75	88	80	eval
85	95	90	92	89	88	eval
80	85	75	60	90	70	eval
85	90	87	80	88	75	eval
85	80	75	50	90	80	eval
95	80	90	85	75	82	eval
85	90	80	70	95	88	eval
90	95	70	85	80	75	eval
90	85	70	75	80	60	eval
95	90	70	50	85	80	eval
80	85	40	60	90	95	eval
75	60	80	55	70	85	eval
90	85	60	50	80	95	eval
45	85	60	20	65	75	eval
85	90	30	60	80	70	eval
90	95	80	40	85	70	[eval](https://sharegpt.com/c/... (truncated for brevity)

🔧 Technical Details

There are no technical implementation details in the original document.

📄 License

The model is licensed under cc - by - nc - 4.0.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご