Infinity-Instruct
A 7.5M high-quality instruction dataset from the Beijing Academy of AI, combining foundational skills (math, code, reasoning) with conversational ability. Used to train models that surpass Llama 3 70B while being much smaller.
from datasets import load_dataset
ds = load_dataset("BAAI/Infinity-Instruct")Preview a sample row
{
"id": "inf_001",
"conversations": [
{"from": "human", "value": "Write a Python function to find all prime numbers up to n using the Sieve of Eratosthenes."},
{"from": "gpt", "value": "def sieve_of_eratosthenes(n):\n primes = [True] * (n+1)\n primes[0] = primes[1] = False\n for i in range(2, int(n**0.5)+1):\n if primes[i]:\n for j in range(i*i, n+1, i):\n primes[j] = False\n return [i for i in range(2, n+1) if primes[i]]"}
]
}Fine-tune with this dataset
Estimated VRAM to fine-tune with QLoRA (4-bit base model + LoRA adapters), using conservative defaults:
New to fine-tuning? Follow the step-by-step walkthrough: Fine-Tune Your First LLM in 1 Hour
Frequently asked questions
Can I use Infinity-Instruct commercially?
Yes — Infinity-Instruct is released under Apache 2.0, a permissive license that allows commercial use, including training models you ship in a product. Check the dataset card for attribution requirements before release.
How much data does Infinity-Instruct contain, and do I need all of it?
Infinity-Instruct contains 7.5M Instructions. You rarely need all of it: for style and format fine-tuning, a few hundred to a few thousand examples are enough — load a slice (e.g. split="train[:1000]") and scale up only if quality plateaus.
What is Infinity-Instruct best used for?
Large-scale general SFT when you need millions of samples. It belongs to the Instruction / SFT section of our dataset hub, where you'll find alternatives and complementary sets.