Mannequin customization transforms general-purpose AI fashions into specialised enterprise property. By fine-tuning basis fashions (FMs) on domain-specific knowledge, 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 duplicate 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 method delivers vital price financial savings whereas protecting delicate knowledge inside safe, personal infrastructure.
Amazon SageMaker AI affords a wide array 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 possibly can adapt these high-performance open-weight fashions to your particular domains and workflows with out provisioning or managing any infrastructure. For an entire record of open fashions out there for serverless mannequin customization, see Customise open weight fashions within the Amazon SageMaker AI documentation.
On this put up, we discover what makes the Nemotron 3 structure distinctive, stroll by the fine-tuning methods out there, and present you step-by-step 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-Specialists (MoE) structure with native help 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-Specialists (LatentMoE) layers that compress tokens earlier than routing to specialised consultants. This design prompts solely a fraction of complete parameters per ahead move (for instance, 12B of 120B within the Tremendous variant), delivering excessive throughput and robust accuracy at considerably decrease compute price. The fashions use multi-environment reinforcement studying by NeMo Gymnasium, which aligns them to real-world, multi-step agentic duties throughout domains equivalent to coding, reasoning, and long-context evaluation.
Nemotron 3 Nano 30B
Nemotron 3 Nano is a small language mannequin optimized for prime 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. Skilled utilizing multi-environment reinforcement studying by NeMo Gymnasium, the mannequin achieves 4x increased throughput than its predecessor Nemotron 2 Nano. Its environment friendly 3B energetic parameter footprint makes it preferrred for high-volume, multi-agent workloads the place price and latency matter. For a deeper take a look at the structure and coaching methods, see the NVIDIA developer weblog.
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 price effectivity. Nemotron 3 Tremendous delivers excessive compute effectivity, throughput, and accuracy for advanced multi-agent purposes equivalent to software program growth and cybersecurity triaging. The mannequin performs nicely at reasoning, coding, and long-context evaluation, whereas remaining environment friendly sufficient to run repeatedly at scale. This makes it a superb match for IT ticket automation, enterprise workflow orchestration, and autonomous agent techniques that require sustained multi-step reasoning. For extra particulars, see the NVIDIA developer weblog on Nemotron 3 Tremendous.
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 possibly can focus in your knowledge, enterprise use case, and analysis, and pay just for what you utilize. You possibly can study extra about SageMaker AI serverless mannequin customization within the AWS documentation.
For Nemotron 3 fashions, SageMaker AI serverless mannequin customization helps the Supervised Superb-Tuning (SFT), Reinforcement Studying with Verifiable Rewards (RLVR) and Reinforcement Studying from AI Suggestions (RLAIF) fine-tuning methods.
| Method | Description | Greatest For |
| Supervised Superb-Tuning (SFT) | Present labeled input-output pairs to show the mannequin new behaviors. | Excessive-quality examples of the conduct you need: area Q&A pairs, formatted software calls, style-aligned responses, or task-specific instruction completions |
| Reinforcement Superb-Tuning (RFT / RLVR) | Use Reinforcement Studying with Verifiable Rewards (RLVR) to optimize mannequin conduct in opposition to 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 aims like software 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 indicators, which helps iterative coverage enchancment with out human-labeled reward knowledge. | 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 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 conduct that base fashions alone can not obtain. With mannequin customization, you possibly can adapt these fashions for industry-specific terminology and choice patterns, prepare dependable software calling together with your group’s APIs, align outputs together with your model voice, refine multi-step agentic reasoning on your architectures, and optimize price by specializing the smaller Nano mannequin to match bigger mannequin efficiency on focused duties.
Getting began with SageMaker AI serverless mannequin customization
You will get began with serverless mannequin customization by 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 knowledge and launch a customization job. Alternatively, for those who’re already working inside SageMaker AI, you should use the agentic performance with agent abilities to speed up your mannequin customization workflow. The next sections stroll you thru the stipulations, knowledge 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 knowledge within the required construction and format.
Put together your coaching knowledge for SageMaker AI serverless mannequin customization
Excessive-quality coaching knowledge is the muse of any profitable fine-tuning job. For serverless mannequin customization on SageMaker AI, your knowledge have to be formatted as JSONL (JSON Traces), the place every line represents a single coaching instance. The precise schema will depend on the method you select: SFT requires conversation-format examples with labeled input-output pairs, whereas RFT (RLVR) requires prompts paired with floor reality values on your reward operate. Correctly structured knowledge 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 knowledge, see the Knowledge Preparation module within the SageMaker AI serverless mannequin customization workshop. Alternatively, if you’re working with SageMaker AI, you should use the built-in coding agent with agent abilities to robotically put together and validate your knowledge formatting, lowering guide effort and serving to you get to coaching quicker.
Mannequin customization in SageMaker AI Studio
Comply with 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 search 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 subsequent step.
- Choose your mannequin customization method from the supported Supervised Superb-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 job necessities. The built-in reward operate (Precise Match, Code Execution, Math Solutions) works nicely for duties with single, objectively appropriate solutions, requiring no extra code. Select a customized reward operate when your job wants richer scoring logic, equivalent to partial credit score, format checks, reasoning high quality analysis, or domain-specific guidelines. With customized reward features, you possibly can rating on a number of indicators, form rewards to keep away from all-zero gradients on early rollouts, emit observability metrics, and encode the Python verification logic your job requires. For detailed steering on authoring and registering a customized reward operate, see the RLVR workshop documentation. - Configure your coaching knowledge by deciding on an current 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 beneficial defaults.
- Select Submit to launch the mannequin customization job.
SageMaker AI robotically provisions the required compute, executes the coaching job, and captures steady logs. The coaching metrics are robotically logged to the SageMaker MLflow App by default for coaching monitoring.
Monitor coaching progress
You possibly can monitor the standing on the mannequin house web page, which shows coaching efficiency, as proven within the following screenshot. A number of high-level metrics are price monitoring. Practice Reward (for RLVR) ought to improve steadily. Coaching Loss and Validation Loss ought to lower and monitor generalization, respectively. Coverage Entropy (for RLVR) decreases because the mannequin positive factors 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 conduct. Within the MLflow monitoring UI, these metrics are organized by the part they measure (actor, critic, rollout, efficiency), so you possibly can diagnose coaching well being at a look.
Consider your fine-tuned mannequin
After coaching completes, you possibly can 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 custom-made mannequin, as proven within the following screenshot. LLM-as-a-Choose makes use of an Amazon Bedrock frontier mannequin to grade responses in opposition to high quality metrics with out requiring ground-truth labels. Customized Scorer applies your individual reward features or built-in scorers to provide customary pure language processing (NLP) metrics equivalent 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.
You can even activate Evaluate 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 custom-made mannequin instantly from the mannequin particulars web page on the console. You can even deploy to SageMaker Inference endpoints, or you possibly can 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 based mostly in your site visitors and throughput necessities. The next screenshot exhibits 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 base 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, it’s also possible to self-host and serve the unmerged LoRA adapter individually, as a result of you’ve got entry to each the bottom weights and the adapter weights in your S3 bucket. After deployment, you invoke the endpoint utilizing the invoke methodology with the AWS Command Line Interface (AWS CLI) or SDK.
Clear up
To keep away from incurring pointless prices, we advocate deleting your SageMaker AI Studio area, SageMaker Endpoints, and every other sources that you just created after you’re carried out utilizing them. The precise price of utilizing SageMaker AI serverless mannequin customization will depend on the bottom mannequin you select and the customization stage. See the Amazon SageMaker AI pricing web page for the associated fee 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 job execution or customizing Nemotron 3 Tremendous for advanced multi-agent orchestration, SageMaker AI handles compute provisioning, coaching orchestration, and metric monitoring so you possibly can focus in your knowledge, 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
