Nectar — LLM Preference (RLHF / DPO) Dataset
A 183K prompt dataset from UC Berkeley with 7 diverse responses per prompt ranked by GPT-4, covering ShareGPT, Alpaca, Open Assistant, LMSYS-Chat, and more. Enables high-quality reward model training with diverse, real-world instruction coverage.
Dataset Details
| Provider | berkeley-nest |
| Category | Preference (RLHF / DPO) |
| Size | 183K Prompts |
| License | Apache 2.0 |
| Downloads | 310k |
| Tags | Reward Model, GPT-4 Ranked, Diverse Sources, Berkeley, RLHF |
from datasets import load_dataset
ds = load_dataset("berkeley-nest/Nectar")
Fine-tune with this dataset
Estimated VRAM to fine-tune with QLoRA (4-bit base model + LoRA adapters), using conservative defaults:
| 7B QLoRA | ~6GB VRAM |
| 13B QLoRA | ~10GB VRAM |
Check if your GPU can fine-tune this →
New to fine-tuning? Follow the step-by-step walkthrough: Fine-Tune Your First LLM in 1 Hour
Related datasets
- HelpSteer2 — Training reward models with fine-grained quality ratings
- UltraFeedback — The default DPO preference set to run after any SFT pass
- Anthropic HH-RLHF — Safety-focused preference training (helpfulness and harmlessness)
- DPO Mix 7K — A small, balanced DPO starter set
Frequently asked questions
Can I use Nectar commercially?
Yes — Nectar 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 Nectar contain, and do I need all of it?
Nectar contains 183K Prompts. 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 Nectar best used for?
Reward-model training with 7-way ranked responses. It belongs to the Preference (RLHF / DPO) section of our dataset hub, where you'll find alternatives and complementary sets.
← All datasets | Fine-Tuning Guide