Enhancing Python Functions with Instructor: A Guide to Fine-Tuning and Distillation¶

Introduction¶

Get ready to dive deep into the world of fine-tuning task specific language models with Python functions. We'll explore how the instructor.instructions streamlines this process, making the task you want to distil more efficient and powerful while preserving its original functionality and backwards compatibility.

If you want to see the full example checkout examples/distillation

Why use Instructor?¶

Imagine you're developing a backend service that uses a mix old and new school ML practises, it may involve pipelines with multiple function calls, validations, and data processing. Sounds cumbersome, right? That's where Instructor comes in. It simplifies complex procedures, making them more efficient and easier to manage by adding a decorator to your function that will automatically generate a dataset for fine-tuning and help you swap out the function implementation.

Quick Start: How to Use Instructor's Distillation Feature¶

Before we dig into the nitty-gritty, let's look at how easy it is to use Instructor's distillation feature to use function calling finetuning to export the data to a JSONL file.

import logging
import random
from pydantic import BaseModel
from instructor import Instructions  # pip install instructor

# Logging setup
logging.basicConfig(level=logging.INFO)

instructions = Instructions(
    name="three_digit_multiply",
    finetune_format="messages",
    # log handler is used to save the data to a file
    # you can imagine saving it to a database or other storage
    # based on your needs!
    log_handlers=[logging.FileHandler("math_finetunes.jsonl")],
)


class Multiply(BaseModel):
    a: int
    b: int
    result: int


# Define a function with distillation
# The decorator will automatically generate a dataset for fine-tuning
# They must return a pydantic model to leverage function calling
@instructions.distil
def fn(a: int, b: int) -> Multiply:
    resp = a * b
    return Multiply(a=a, b=b, result=resp)


# Generate some data
for _ in range(10):
    a = random.randint(100, 999)
    b = random.randint(100, 999)
    print(fn(a, b))
    #> a=873 b=234 result=204282
    #> a=902 b=203 result=183106
    #> a=962 b=284 result=273208
    #> a=491 b=739 result=362849
    #> a=193 b=400 result=77200
    #> a=300 b=448 result=134400
    #> a=952 b=528 result=502656
    #> a=574 b=797 result=457478
    #> a=482 b=204 result=98328
    #> a=781 b=278 result=217118

The Intricacies of Fine-tuning Language Models¶

Fine-tuning isn't just about writing a function like def f(a, b): return a * b. It requires detailed data preparation and logging. However, Instructor provides a built-in logging feature and structured outputs to simplify this.

Why Instructor and Distillation are Game Changers¶

The library offers two main benefits:

1. Efficiency: Streamlines functions, distilling requirements into model weights and a few lines of code.
2. Integration: Eases combining classical machine learning and language models by providing a simple interface that wraps existing functions.

Role of Instructor in Simplifying Fine-Tuning¶

The from instructor import Instructions feature is a time saver. It auto-generates a fine-tuning dataset, making it a breeze to imitate a function's behavior.

Logging Output and Running a Finetune¶

Here's how the logging output would look:

{
    "messages": [
        {"role": "system", "content": 'Predict the results of this function: ...'},
        {"role": "user", "content": 'Return fn(133, b=539)'},
        {
            "role": "assistant",
            "function_call": {
                "name": "Multiply",
                "arguments": '{"a":133,"b":539,"result":89509}',
            },
        },
    ],
    "functions": [
        {"name": "Multiply", "description": "Correctly extracted `Multiply`..."}
    ],
}

Run a finetune like this:

instructor jobs create-from-file math_finetunes.jsonl

Next Steps and Future Plans¶

Here's a sneak peek of what I'm planning:

from instructor import Instructions, patch

patch()  # (1)!


class Multiply(BaseModel):
    a: int
    b: int
    result: int


instructions = Instructions(
    name="three_digit_multiply",
)


@instructions.distil(model='gpt-3.5-turbo:finetuned-123', mode="dispatch")  # (2)!
def fn(a: int, b: int) -> Multiply:
    resp = a + b
    return Multiply(a=a, b=b, result=resp)

1. Don't forget to run the patch() command that we provide with the Instructor package. This helps automatically serialize the content back into the `Pydantic`` model that we're looking for.

2. Don't forget to replace this with your new model id. OpenAI identifies fine tuned models with an id of ft:gpt-3.5-turbo-0613:personal::<id> under their Fine-tuning tab on their dashboard

With this, you can swap the function implementation, making it backward compatible. You can even imagine using the different models for different tasks or validating and runnign evals by using the original function and comparing it to the distillation.

Conclusion¶

We've seen how Instructor can make your life easier, from fine-tuning to distillation. Now if you're thinking wow, I'd love a backend service to do this for continously, you're in luck! Please check out the survey at useinstructor.com and let us know who you are.

If you enjoy the content or want to try out instructor please check out the github and give us a star!