instructify 0.0.3

Instructify 📝 for easy Fine-Tuning preparation

Instructify 📝

Instructify is a Python library designed to convert CSV files or Hugging Face datasets into Hugging Face Dataset objects, specifically formatted for fine-tuning large language models (LLMs). Inspired by the instruction-based dataset approach described in OpenAI's InstructGPT paper (2203.02155), this package helps prepare your data for instruction-based tasks using a chat-like format.

Features ✨

• CSV or Hugging Face Dataset Support: Automatically detect whether the input is a CSV file or a Hugging Face dataset.
• Customizable Message Formatting: Supports user, assistant, and system messages with flexible column names.
• Tokenizer Integration: Automatically integrates with a pre-trained tokenizer to format messages.
• Custom Templates: Apply a custom template or use the tokenizer's default chat format.
• Easy Fine-Tuning Preparation: Prepares data for instruction tuning, similar to the InstructGPT format.

Installation 📦

pip install instructify

Usage 🚀

CSV Input

import pandas as pd
from instructify import to_train_dataset

# Example custom template
custom_template = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}

### Input:
{}

### Response:
{}"""

# Example data
data = {
    "input": ["When was the Library of Alexandria burned down?", "What is the capital of France?"],
    "output": ["I-I think that was in 48 BC, b-but I'm not sure.", "The capital of France is Paris."],
    "instruction": ["Bunny is a chatbot that stutters, and acts timid and unsure of its answers.", None]
}

# Convert data to CSV
df = pd.DataFrame(data)
df.to_csv("data.csv", index=False)

# Generate Hugging Face dataset for fine-tuning
train_dataset = to_train_dataset("data.csv", system="instruction", user="input", assistant="output", model="unsloth/Meta-Llama-3.1-8B-Instruct", custom_template=custom_template)

# Inspect the formatted dataset
print(train_dataset["text"])

Hugging Face Dataset Input

from instructify import to_train_dataset

# Example custom template
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{}

### Input:
{}

### Response:
{}"""

# Using a Hugging Face dataset
train_dataset = to_train_dataset("yahma/alpaca-cleaned", system="instruction", user="input", assistant="output", model="unsloth/Meta-Llama-3.1-8B-Instruct", custom_template=alpaca_prompt)

# Inspect the formatted dataset
print(train_dataset["text"])

Output Example 📄

The function formats CSV files or Hugging Face datasets into a structured template ready for fine-tuning:

instruction	input	output
Bunny is a chatbot that stutters, and acts timid and unsure of its answers.	When was the Library of Alexandria burned down?	I-I think that was in 48 BC, b-but I'm not sure.
None	What is the capital of France?	The capital of France is Paris.

Default Output Format

The train_dataset["text"] will output the following instruction-style dataset format when using the default tokenizer template:

[
    "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\nBunny is a chatbot that stutters, and acts timid and unsure of its answers.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhen was the Library of Alexandria burned down?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nI-I think that was in 48 BC, b-but I'm not sure.<|eot_id|>",
    
    "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nCutting Knowledge Date: December 2023\nToday Date: 26 Jul 2024\n\n<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nWhat is the capital of France?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\nThe capital of France is Paris.<|eot_id|>"
]

Custom Template Output

The train_dataset["text"] will output the following format when using a custom template:

[
    "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\nBunny is a chatbot that stutters, and acts timid and unsure of its answers.\n\n### Input:\nWhen was the Library of Alexandria burned down?\n\n### Response:\nI-I think that was in 48 BC, b-but I'm not sure.<|eot_id|>",
    
    "Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\n\n\n### Input:\nWhat is the capital of France?\n\n### Response:\nThe capital of France is Paris.<|eot_id|>"
]

Functionality Overview 🔍

to_train_dataset

This function is the core of the library, enabling both CSV and Hugging Face dataset conversion for LLM fine-tuning.

Parameters:

• data_source: Path to the input CSV file or Hugging Face dataset identifier.
• system (optional): Column name for system messages (e.g., instructions for the model).
• user: Column name for user messages (default: 'user').
• assistant: Column name for assistant messages (default: 'assistant').
• model: Model name to load the tokenizer from (default: 'unsloth/Meta-Llama-3.1-8B-Instruct').
• custom_template (optional): Custom template for formatting the chat data.

Returns:

• Dataset: A Hugging Face Dataset, ready for LLM fine-tuning.

License ⚖️

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.

Contributing 🤝

We welcome contributions! Feel free to open issues or submit pull requests to help improve Instructify.