Mannequin customization transforms general-purpose AI fashions into specialised enterprise belongings. By fine-tuning basis fashions (FMs) on domain-specific information, companies educate AI their distinctive workflows, terminology, and deep area specialization, together with strict adherence to model voice and fewer hallucinations. For enterprises, that is greater than an optimization. It’s the creation of proprietary mental property. A fine-tuned mannequin encodes a company’s distinctive intelligence and finest practices into its structure. This builds a aggressive benefit that’s tough to copy with off-the-shelf public frontier fashions. On the similar time, fine-tuning smaller, open-weight fashions on focused duties typically matches or exceeds the efficiency of a lot bigger proprietary fashions. This strategy delivers vital value financial savings whereas protecting delicate information inside safe, non-public infrastructure.
Amazon SageMaker AI presents a big selection of open supply fashions and fine-tuning methods to assist organizations tailor basis fashions to their distinctive wants. Now, SageMaker AI introduces serverless mannequin customization for NVIDIA Nemotron 3 fashions, beginning with Nemotron 3 Nano (30B complete parameters, 3B energetic) and Nemotron 3 Tremendous (120B complete parameters, 12B energetic). With supervised fine-tuning (SFT), reinforcement studying with verifiable rewards (RLVR), and reinforcement studying with AI suggestions (RLAIF), you may adapt these high-performance open-weight fashions to your particular domains and workflows with out provisioning or managing any infrastructure. For a whole record of open fashions out there for serverless mannequin customization, see Customise open weight fashions within the Amazon SageMaker AI documentation.
On this publish, we discover what makes the Nemotron 3 structure distinctive, stroll by way of the fine-tuning methods out there, and present you step-by-step learn how to get began with serverless customization utilizing SageMaker Studio.
Overview of NVIDIA Nemotron 3 fashions on Amazon SageMaker AI
NVIDIA Nemotron 3 is a household of open-weight massive language fashions (LLMs) constructed on a hybrid Mamba-Transformer Combination-of-Consultants (MoE) structure with native assist for as much as 1M-token context lengths. The structure interleaves three complementary layer varieties: Mamba-2 layers for environment friendly linear-time sequence processing, Transformer consideration layers for exact associative recall, and Latent Combination-of-Consultants (LatentMoE) layers that compress tokens earlier than routing to specialised consultants. This design prompts solely a fraction of complete parameters per ahead cross (for instance, 12B of 120B within the Tremendous variant), delivering excessive throughput and robust accuracy at considerably decrease compute value. The fashions use multi-environment reinforcement studying by way of NeMo Fitness center, which aligns them to real-world, multi-step agentic duties throughout domains comparable to coding, reasoning, and long-context evaluation.
Nemotron 3 Nano 30B
Nemotron 3 Nano is a small language mannequin optimized for top compute effectivity whereas sustaining robust accuracy on specialised duties. Nemotron 3 Nano performs strongly on coding and reasoning duties amongst open language fashions in its dimension class. Educated utilizing multi-environment reinforcement studying by way of NeMo Gym, the mannequin achieves 4x greater throughput than its predecessor Nemotron 2 Nano. Its environment friendly 3B energetic parameter footprint makes it best for high-volume, multi-agent workloads the place value and latency matter. For a deeper have a look at the structure and coaching methods, see the NVIDIA developer blog.
Nemotron 3 Tremendous 120B
Nemotron 3 Tremendous is a bigger mannequin designed for high-efficiency multi-agent AI and complicated reasoning duties that require extra capability than Nano whereas sustaining value effectivity. Nemotron 3 Tremendous delivers excessive compute effectivity, throughput, and accuracy for advanced multi-agent purposes comparable to software program growth and cybersecurity triaging. The mannequin performs properly at reasoning, coding, and long-context evaluation, whereas remaining environment friendly sufficient to run repeatedly at scale. This makes it an excellent match for IT ticket automation, enterprise workflow orchestration, and autonomous agent programs that require sustained multi-step reasoning. For extra particulars, see the NVIDIA developer blog on Nemotron 3 Super.
SageMaker AI serverless mannequin customization
Amazon SageMaker AI serverless mannequin customization removes the undifferentiated heavy lifting of fine-tuning. You don’t have to provision GPU clusters, configure distributed coaching frameworks, or handle checkpointing and fault tolerance. SageMaker AI handles infrastructure provisioning and coaching orchestration, so you may focus in your information, enterprise use case, and analysis, and pay just for what you utilize. You may study extra about SageMaker AI serverless mannequin customization within the AWS documentation.
For Nemotron 3 fashions, SageMaker AI serverless mannequin customization helps the Supervised Wonderful-Tuning (SFT), Reinforcement Studying with Verifiable Rewards (RLVR) and Reinforcement Studying from AI Suggestions (RLAIF) fine-tuning methods.
| Method | Description | Finest For |
| Supervised Wonderful-Tuning (SFT) | Present labeled input-output pairs to show the mannequin new behaviors. | Excessive-quality examples of the habits you need: area Q&A pairs, formatted instrument calls, style-aligned responses, or task-specific instruction completions |
| Reinforcement Wonderful-Tuning (RFT / RLVR) | Use Reinforcement Studying with Verifiable Rewards (RLVR) to optimize mannequin habits towards a reward sign. The mannequin generates a number of candidate responses per immediate, a reward operate scores them, and the mannequin updates its coverage to favor what works. | Duties with naturally verifiable goals like instrument calling accuracy, code correctness, or format compliance |
| Reinforcement Studying from AI Suggestions (RLAIF) | Use a separate AI mannequin to information the mannequin optimization. An AI mannequin evaluates mannequin outputs and offers suggestions alerts, which helps iterative coverage enchancment with out human-labeled reward information. | Aligning mannequin tone, helpfulness, and security; enhancing response high quality when human analysis is dear or subjective; refining open-ended technology duties |
Let’s stroll by way of learn how to get began with serverless mannequin customization for Nemotron 3 fashions. Whereas the bottom Nemotron 3 fashions ship robust general-purpose efficiency, enterprise use circumstances want domain-specific habits that base fashions alone can’t obtain. With mannequin customization, you may adapt these fashions for industry-specific terminology and choice patterns, prepare dependable instrument calling along with your group’s APIs, align outputs along with your model voice, refine multi-step agentic reasoning on your architectures, and optimize value by specializing the smaller Nano mannequin to match bigger mannequin efficiency on focused duties.
Getting began with SageMaker AI serverless mannequin customization
You may get began with serverless mannequin customization by way of the Amazon SageMaker Studio console or programmatically utilizing the SageMaker Python SDK. On the console, navigate to the Fashions web page, choose your Nemotron 3 mannequin, and observe the guided workflow to configure your coaching information and launch a customization job. Alternatively, for those who’re already working inside SageMaker AI, you should utilize the agentic performance with agent expertise to speed up your mannequin customization workflow. The next sections stroll you thru the conditions, information preparation, and step-by-step directions utilizing the SageMaker Studio console. For an in depth programmatic instance with the SageMaker Python SDK for customizing an open-source mannequin, see the AWS samples GitHub repository.
Conditions
Earlier than you start, confirm that you’ve got:
- An AWS account with AWS Id and Entry Administration (IAM) permissions for Amazon SageMaker AI.
- A SageMaker AI area with Studio entry.
- Your coaching information within the required construction and format.
Put together your coaching information for SageMaker AI serverless mannequin customization
Excessive-quality coaching information is the muse of any profitable fine-tuning job. For serverless mannequin customization on SageMaker AI, your information should be formatted as JSONL (JSON Strains), the place every line represents a single coaching instance. The particular schema is dependent upon the method you select: SFT requires conversation-format examples with labeled input-output pairs, whereas RFT (RLVR) requires prompts paired with floor fact values on your reward operate. Correctly structured information ensures the mannequin learns the behaviors you plan with out introducing noise or formatting errors. For a hands-on walkthrough of making ready your coaching information, see the Data Preparation module in the SageMaker AI serverless model customization workshop. Alternatively, in case you are working with SageMaker AI, you should utilize the built-in coding agent with agent skills to automatically prepare and validate your information formatting, lowering guide effort and serving to you get to coaching sooner.
Mannequin customization in SageMaker AI Studio
Observe these steps to customise a Nemotron 3 mannequin utilizing the SageMaker AI Studio console.
- Open Amazon SageMaker AI Studio and within the left navigation pane, select Fashions.
- Navigate to the mannequin you need to customise within the UI. Seek for “NVIDIA” to seek out the Nemotron 3 household of fashions, and choose the NVIDIA mannequin that you really want (
NVIDIA-Nemotron-3-Nano-30B-*orNVIDIA-Nemotron-3-Tremendous-120B-*) for the following step.
- Choose your mannequin customization method from the supported Supervised Wonderful-Tuning (SFT), Reinforcement Studying with Verifiable Rewards (RLVR) and Reinforcement Studying from AI Suggestions (RLAIF) fine-tuning methods.
When selecting a reward operate sort for RLVR, contemplate your process necessities. The built-in reward operate (Actual Match, Code Execution, Math Solutions) works properly for duties with single, objectively appropriate solutions, requiring no extra code. Select a customized reward operate when your process wants richer scoring logic, comparable to partial credit score, format checks, reasoning high quality analysis, or domain-specific guidelines. With customized reward features, you may rating on a number of alerts, form rewards to keep away from all-zero gradients on early rollouts, emit observability metrics, and encode the Python verification logic your process requires. For detailed steerage on authoring and registering a customized reward operate, see the RLVR workshop documentation. - Configure your coaching information by choosing an present dataset (if out there) or creating a brand new dataset (see the previous part for details about making ready your dataset).
- Set the customization hyperparameters or use really helpful defaults.
- Select Submit to launch the mannequin customization job.
SageMaker AI mechanically provisions the required compute, executes the coaching job, and captures steady logs. The coaching metrics are mechanically logged to the SageMaker MLflow App by default for coaching monitoring.
Monitor coaching progress
You may monitor the standing on the mannequin dwelling web page, which shows coaching efficiency, as proven within the following screenshot. A number of high-level metrics are value monitoring. Prepare Reward (for RLVR) ought to enhance steadily. Coaching Loss and Validation Loss ought to lower and monitor generalization, respectively. Coverage Entropy (for RLVR) decreases because the mannequin beneficial properties confidence. Gradient Norm ought to stabilize to point convergence.
The detailed coaching and validation metrics are additionally logged to the related SageMaker AI MLflow App, as proven within the following screenshot. This captures a complete set of metrics and parameters that monitor coaching progress, and mannequin habits. Within the MLflow monitoring UI, these metrics are organized by the element they measure (actor, critic, rollout, efficiency), so you may diagnose coaching well being at a look.
Consider your fine-tuned mannequin
After coaching completes, you may consider the fine-tuned mannequin utilizing the built-in analysis options of SageMaker AI serverless mannequin customization. It offers three strategies to evaluate the standard of your personalized mannequin, as proven within the following screenshot. LLM-as-a-Choose makes use of an Amazon Bedrock frontier mannequin to grade responses towards high quality metrics with out requiring ground-truth labels. Customized Scorer applies your individual reward features or built-in scorers to provide normal pure language processing (NLP) metrics comparable to F1, ROUGE, and BLEU. Benchmarks scores your mannequin on standardized tutorial benchmarks (MMLU, BBH, GPQA, MATH, IFEval) for broad functionality evaluation throughout reasoning, information, and instruction-following.
It’s also possible to activate Examine with base mannequin in analysis to instantly measure how your post-trained mannequin performs relative to the bottom mannequin. Along with the earlier coaching metrics, MLflow tracks the coaching dynamics (rewards, KL divergence, loss). The analysis measures output high quality from an end-user perspective, supplying you with an entire image of the mannequin fine-tuning effectiveness.
Deploy the fine-tuned mannequin
Deploy your personalized mannequin instantly from the mannequin particulars web page on the console. It’s also possible to deploy to SageMaker Inference endpoints, or you may obtain mannequin weights from an Amazon Easy Storage Service (Amazon S3) bucket for self-managed deployment. The deployment choices auto-populate defaults, supplying you with full flexibility over compute and scaling primarily based in your visitors and throughput necessities. The next screenshot reveals the deployment of the fine-tuned NVIDIA Nemotron Nano 30B utilizing an ml.g6e occasion powered by NVIDIA L40S Tensor Core GPUs. The deployment makes use of SageMaker inference elements and, by default, serves the merged mannequin weights, the place the bottom mannequin and LoRA adapter are mixed right into a single set of weights for optimized inference. As a result of it is a LoRA fine-tune, you may also self-host and serve the unmerged LoRA adapter individually, as a result of you could have entry to each the bottom weights and the adapter weights in your S3 bucket. After deployment, you invoke the endpoint utilizing the invoke technique with the AWS Command Line Interface (AWS CLI) or SDK.
Clear up
To keep away from incurring pointless fees, we advocate deleting your SageMaker AI Studio area, SageMaker Endpoints, and some other sources that you just created after you’re achieved utilizing them. The particular value of utilizing SageMaker AI serverless mannequin customization is dependent upon the bottom mannequin you select and the customization stage. See the Amazon SageMaker AI pricing web page for the price breakdown and particulars.
Conclusion
With serverless mannequin customization for NVIDIA Nemotron 3 fashions on Amazon SageMaker AI, now you can adapt these high-performance open-weight fashions to your particular domains and workflows. Whether or not you’re fine-tuning Nemotron 3 Nano for cost-efficient agentic process execution or customizing Nemotron 3 Tremendous for advanced multi-agent orchestration, SageMaker AI handles compute provisioning, coaching orchestration, and metric monitoring so you may focus in your information, analysis, and deployment.
Get began at the moment with serverless Mannequin Customization on Amazon SageMaker AI. For detailed examples of customizing open-source fashions, see the AWS samples GitHub repository. To study extra, see the Amazon SageMaker AI mannequin customization documentation.
Concerning the authors
