Overview

This is a fine-tuned 7b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros

The dataset used to fine-tune this model is available here, with a specific focus on:

• trivia
• math/reasoning (although it still sucks)
• coding
• multiple choice and fill-in-the-blank
• context-obedient question answering
• theory of mind
• misc/general

This model was fine-tuned with a fork of FastChat, and therefore uses the standard vicuna template:

A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. USER: [prompt] ASSISTANT:

So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).

The most important bit, to me, is the context obedient question answering support, without extensive prompt engineering.

Note: the example prompt response pairs below are from the 13b model, YMMV with the 7b

Usage

The easiest way to get started is to use my fork of FastChat, which is mostly the same but allows for the increased context length and adds support for multi-line inputs:

pip install git+https://github.com/jondurbin/FastChat

Then, you can invoke it like so (after downloading the model):

python -m fastchat.serve.cli
 --model-path airoboros-7b-gpt4 \
 --temperature 0.5 \
 --no-history

Context obedient question answering

By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.

The format for a closed-context prompt is as follows:

BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION

Here's a trivial, but important example to prove the point:

BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION

And the response:

Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123

Other stuff

Better coding

Example:

Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate

Word games / trivia

USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen

USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging

Multiple choice

USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?

A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: [C, Pluto]

Writing

Usage and License Notices

All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:

• the base model is LLaMa, which has it's own special research license
• the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai

So, to reiterate: this model (and datasets) cannot be used commercially.