At this time, we’re excited to announce two main enhancements to mannequin fine-tuning in Azure AI Foundry—Reinforcement Effective-Tuning (RFT) with o4-mini, coming quickly, and Supervised Effective-Tuning (SFT) for the 4.1-nano mannequin, obtainable now.
At this time, we’re excited to announce three main enhancements to mannequin fine-tuning in Azure AI Foundry—Reinforcement Effective-Tuning (RFT) with o4-mini (coming quickly), Supervised Effective-Tuning (SFT) for the GPT-4.1-nano and Llama 4 Scout mannequin (obtainable now). These updates mirror our continued dedication to empowering organizations with instruments to construct extremely personalized, domain-adapted AI techniques for real-world affect.
With these new fashions, we’re unblocking two main avenues of LLM customization: GPT-4.1-nano is a robust small mannequin, very best for distillation, whereas o4-mini is the primary reasoning mannequin you may fine-tune, and Llama 4 Scout is a best-in-class open supply mannequin.
Reinforcement Effective-Tuning with o4-mini
Reinforcement Effective-Tuning introduces a brand new stage of management for aligning mannequin habits with advanced enterprise logic. By rewarding correct reasoning and penalizing undesirable outputs, RFT improves mannequin decision-making in dynamic or high-stakes environments.
Coming quickly for the o4-mini mannequin, RFT unlocks new potentialities to be used circumstances requiring adaptive reasoning, contextual consciousness, and domain-specific logic—all whereas sustaining quick inference efficiency.
Actual world affect: DraftWise
DraftWise, a authorized tech startup, used reinforcement fine-tuning (RFT) in Azure AI Foundry Fashions to boost the efficiency of reasoning fashions tailor-made for contract technology and overview. Confronted with the problem of delivering extremely contextual, legally sound recommendations to attorneys, DraftWise fine-tuned Azure OpenAI fashions utilizing proprietary authorized information to enhance response accuracy and adapt to nuanced person prompts. This led to a 30% enchancment in search end result high quality, enabling attorneys to draft contracts quicker and give attention to high-value advisory work.
Reinforcement fine-tuning on reasoning fashions is a possible recreation changer for us. It’s serving to our fashions perceive the nuance of authorized language and reply extra intelligently to advanced drafting directions, which guarantees to make our product considerably extra helpful to attorneys in actual time.
—James Ding, founder and CEO of DraftWise.
When do you have to use Reinforcement Effective-Tuning?
Reinforcement Effective-Tuning is finest suited to use circumstances the place adaptability, iterative studying, and domain-specific habits are important. It’s best to think about RFT in case your state of affairs includes:
- Customized Rule Implementation: RFT thrives in environments the place choice logic is very particular to your group and can’t be simply captured via static prompts or conventional coaching information. It allows fashions to study versatile, evolving guidelines that mirror real-world complexity.
- Area-Particular Operational Requirements: Supreme for situations the place inner procedures diverge from trade norms—and the place success depends upon adhering to these bespoke requirements. RFT can successfully encode procedural variations, reminiscent of prolonged timelines or modified compliance thresholds, into the mannequin’s habits.
- Excessive Resolution-Making Complexity: RFT excels in domains with layered logic and variable-rich choice bushes. When outcomes rely upon navigating quite a few subcases or dynamically weighing a number of inputs, RFT helps fashions generalize throughout complexity and ship extra constant, correct selections.
Instance: Wealth advisory at Contoso Wellness
To showcase the potential of RFT, think about Contoso Wellness, a fictitious wealth advisory agency. Utilizing RFT, the o4-mini mannequin realized to adapt to distinctive enterprise guidelines, reminiscent of figuring out optimum shopper interactions primarily based on nuanced patterns just like the ratio of a shopper’s internet price to obtainable funds. This enabled Contoso to streamline their onboarding processes and make extra knowledgeable selections quicker.
Supervised Effective-Tuning now obtainable for GPT-4.1-nano
We’re additionally bringing Supervised Effective-Tuning (SFT) to the GPT-4.1-nano mannequin—a small however highly effective basis mannequin optimized for high-throughput, cost-sensitive workloads. With SFT, you may instill your mannequin with company-specific tone, terminology, workflows, and structured outputs—all tailor-made to your area. This mannequin can be obtainable for fine-tuning within the coming days.
Why Effective-tune GPT-4.1-nano?
- Precision at Scale: Tailor the mannequin’s responses whereas sustaining pace and effectivity.
- Enterprise-Grade Output: Guarantee alignment with enterprise processes and tone-of-voice.
- Light-weight and Deployable: Excellent for situations the place latency and price matter—reminiscent of customer support bots, on-device processing, or high-volume doc parsing.
In comparison with bigger fashions, 4.1-nano delivers quicker inference and decrease compute prices, making it effectively suited to large-scale workloads like:
- Buyer help automation, the place fashions should deal with 1000’s of tickets per hour with constant tone and accuracy.
- Inside data assistants that observe firm model and protocol in summarizing documentation or responding to FAQs.
As a small, quick, however extremely succesful mannequin, GPT-4.1-nano makes a fantastic candidate for distillation as effectively. You need to use fashions like GPT-4.1 or o4 to generate coaching information—or seize manufacturing visitors with saved completions—and educate 4.1-nano to be simply as sensible!
Llama 4 Effective-Tuning now obtainable
We’re additionally excited to announce help for fine-tuning Meta’s Llama 4 Scout—a leading edge,17 billion energetic parameter mannequin which presents an trade main context window of 10M tokens whereas becoming on a single H100 GPU for inferencing. It’s a best-in-class mannequin, and extra highly effective than all earlier technology llama fashions.
Llama 4 fine-tuning is obtainable in our managed compute providing, permitting you to fine-tune and inference utilizing your individual GPU quota. Accessible in each Azure AI Foundry and as Azure Machine Studying parts, you have got entry to further hyperparameters for deeper customization in comparison with our serverless expertise.
Get began with Azure AI Foundry at the moment
Azure AI Foundry is your basis for enterprise-grade AI tuning. These fine-tuning enhancements unlock new frontiers in mannequin customization, serving to you construct clever techniques that assume and reply in ways in which mirror your corporation DNA.
- Use Reinforcement Effective-tuning with o4-mini to construct reasoning engines that study from expertise and evolve over time. Coming quickly in Azure AI Foundry, with regional availability for East US2 and Sweden Central.
- Use Supervised Effective-Tuning with 4.1-nano to scale dependable, cost-efficient, and extremely personalized mannequin behaviors throughout your group. Accessible now in Azure AI Foundry in North Central US and Sweden Central.
- Strive Llama 4 scout superb tuning to customise a best-in-class open supply mannequin. Accessible now in Azure AI Foundry mannequin catalog and Azure Machine Studying.
With Azure AI Foundry, fine-tuning isn’t nearly accuracy—it’s about belief, effectivity, and adaptableness at each layer of your stack.
Discover additional:
We’re simply getting began. Keep tuned for extra mannequin help, superior tuning methods, and instruments that will help you construct AI that’s smarter, safer, and uniquely yours.