Sold by: Synthefy
Deployed on AWS
Fine-tune the Synthefy-Nori tabular regression model on your own CSV table with an Amazon SageMaker training job in your AWS account, then serve the fine-tuned model from an asynchronous SageMaker endpoint under a name you choose. The job starts from a released Nori base (nori-6m or nori-100m), adapts it to your table and reports the validation error of the base and of the fine-tuned model on the same rows, so you can see what fine-tuning bought before you deploy.
Overview
Synthefy-Nori is a transformer for tabular regression that learns in context: each prediction request carries labeled rows (X_train, y_train) and the rows to predict (X_test), and the model predicts them in one forward pass without a training step. This algorithm adds a training step for a table you predict on repeatedly: it adapts a released Nori base to that table and serves the result with the same request format, so you still send fresh context rows with every prediction.
What the job does. It reads your CSV from an S3 channel, trains a fine-tuned model on it with a few settings you may change (the base model, the number of children the job trains, the step and time budget per child, the learning rate, the seed), and writes a model artifact and a training report to your bucket. The artifact is small: it holds what changed relative to the base, and the base itself stays inside the container.
What the report tells you. Before training, the job sets aside rows that no training step sees: 10 percent of your rows up to 4,096, or the rows of your validation channel when you give one. It scores the base model and the fine-tuned model on those rows with the same context and writes both mean squared errors, val_mse_before and val_mse_after, to training_report.json, together with each child's curve, the rows read and used, and whether the job was cut short. Compare the two numbers before you deploy: fine-tuning does not improve every table.
Use case. You predict one numeric target repeatedly from one table of at least 1,000 rows and want a model adapted to that table while keeping Nori's in-context request format.
Scope of this version. Regression only. CSV input only: one header row, numeric columns, a finite target in every row. Trainable bases: nori-6m (24 GB or 48 GB GPU) and nori-100m (48 GB GPU, ml.g6e types only). One training instance per job; distributed training and automatic model tuning are not offered. The fine-tuned model is served from an asynchronous SageMaker endpoint and answers only to the name you set in the model_name hyperparameter, which starts with ft-.
Where it runs. The training job, the model package and the endpoint run in your AWS account with network isolation, and your data stays in your S3 buckets. No Synthefy service is in the path, and Synthefy can neither see nor stop your jobs or endpoints. The synthefy Python package (pip install "synthefy[aws]>=7.2.0") starts and follows the job, deploys the result and calls the endpoint; plain AWS SDK or CLI calls work as well.
Highlights
- Fine-tunes Nori (nori-6m or nori-100m) on a CSV table of 1,000 or more rows in a single-instance GPU training job. The artifact holds only what changed relative to the base, not a copy of the model.
- Every job reports val_mse_before and val_mse_after: the base and the fine-tuned model scored on the same held-out rows with the same context, so you know what fine-tuning bought before you deploy.
- Runs in your AWS account with network isolation: the training job, model package and asynchronous endpoint are yours, and the endpoint serves the fine-tuned model under the ft- name you choose.
Details
Sold by
Categories
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
This product is available free of charge. Free subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimensions summary
You pay by the hour for the compute instance you run, metered as host hours. Pricing splits into two activities: training and inference. Training runs on five GPU instance types, from the ml.g5 and ml.g6 families, each billed at its own hourly rate. Inference runs in two modes: real-time, offered on three instance types, and batch, offered on two. Larger instance sizes within a family carry a different hourly rate than smaller ones. You choose the instance and mode that match your workload, with no upfront commitment.
Top-of-mind questions for buyers
A host hour meters one running compute instance for one hour. Billing counts the wall-clock time the instance stays active, rounded by the hour. Each instance type carries its own hourly rate. Stopped or terminated instances stop accruing software charges.
Both modes bill by host hours on the instance you run. Real-time inference keeps an instance active to answer requests as they arrive, so you pay while it stays warm. Batch inference runs over a dataset and bills for the time the job takes, then stops.
Yes. A real-time instance bills per host hour for as long as it stays active, even between requests. The hosted model can scale to zero when idle, and a cold start takes about 60 to 90 seconds; warm requests return in one to two seconds.
docs.synthefy.com
Helpful?
Vendor refund policy
Synthefy-Nori Fine-Tuning is offered free of charge on AWS Marketplace, so there are no software fees to refund. Buyers pay only their own AWS infrastructure costs (for example, SageMaker training and endpoint instance charges), which are billed directly by AWS and are outside Synthefy's control. For any questions, contact support@synthefy.com .
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker algorithm
An Amazon SageMaker algorithm is a machine learning model that requires your training data to make predictions. Use the included training algorithm to generate your unique model artifact. Then deploy the model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Initial AWS Marketplace release of the Synthefy-Nori fine-tuning algorithm.
Training
- Fine-tunes nori-6m (default) or nori-100m on a CSV table in a single-instance GPU training job.
- Channels: train (required) and validation (optional), text/csv, File mode.
- Settings: target_column and model_name (required); base_model, feature_columns, bag (the number of children the job trains, 1 to 8), steps and budget_s per child, lr, patience, seed. None is tunable.
- training_report.json records val_mse_before and val_mse_after on the same held-out rows, each child's curve, the rows read and used, and whether the job was cut short.
Serving
- A model package created from a job serves the fine-tuned model on an asynchronous SageMaker endpoint under the ft- name set in model_name.
- The artifact holds what changed relative to the base; the endpoint's container holds the base itself and checks it by digest before serving.
Instance types
- Training: ml.g5.xlarge, ml.g5.2xlarge, ml.g6.xlarge (nori-6m); ml.g6e.xlarge, ml.g6e.2xlarge (nori-6m and nori-100m).
- Endpoint: ml.g5.xlarge, ml.g5.2xlarge, ml.g6.xlarge.
Client
- synthefy 7.2.0 or later: SynthefyNoriFineTuner starts, follows, deploys and undeploys; SynthefyNoriClient(mode="sagemaker") calls the endpoint.
Additional details
Inputs
- Summary
The fine-tuned model keeps Nori's in-context request format: each request carries labeled context rows and the rows to predict, and the response has one prediction per query row.
Content type: application/json (SynthefyNoriClient sends the same request as application/vnd.synthefy.nori.tensorfile).
Request body (one JSON object):
- model: required string, the fine-tuned model's name, equal to the model_name hyperparameter of the training job (ft-...). Any other value is refused.
- X_train: required array of arrays, the labeled context rows, shape [n_context][n_features]. Numbers or null.
- y_train: required array of numbers, one finite target per X_train row, aligned by position.
- X_test: required array of arrays, the rows to predict, with the same columns in the same order as X_train.
- task: optional string, "regression" (the default and only value).
Use the training table's feature columns, in training order, without the target, encoded the same way as for training.
Asynchronous endpoint: the request is an object in your S3 staging prefix passed to InvokeEndpointAsync. Batch transform: one request per S3 object (SplitType None).
- Limitations for input type
- Regression only. Features must be numeric (missing values may be null); encode categorical columns before sending. X_train and X_test must have the same number of columns in the same order. SageMaker Asynchronous Inference accepts an input object up to 1 GB and processes an invocation for up to one hour; practical table size depends on GPU and host memory. The client does not split oversized requests.
- Input MIME type
- application/json
{"model":"ft-marketplace-validation","task":"regression","X_train":[[0.12,-1.05,0.33,0.80,-0.41,1.20,0.05,-0.66],[-0.73,0.48,-1.12,0.27,0.90,-0.35,1.41,0.18],[1.05,0.22,0.61,-0.94,-1.30,0.44,-0.27,0.73],[-0.38,-0.59,0.95,1.16,0.21,-0.88,0.62,-1.02]],"y_train":[0.31,0.87,-0.42,1.64],"X_test":[[0.40,-0.20,0.10,0.55,-0.75,0.30,0.95,-0.15],[-1.10,0.85,-0.45,-0.60,0.35,1.05,-0.50,0.25]]}
{"model":"ft-marketplace-validation","task":"regression","X_train":[[0.12,-1.05,0.33,0.80,-0.41,1.20,0.05,-0.66],[-0.73,0.48,-1.12,0.27,0.90,-0.35,1.41,0.18],[1.05,0.22,0.61,-0.94,-1.30,0.44,-0.27,0.73],[-0.38,-0.59,0.95,1.16,0.21,-0.88,0.62,-1.02]],"y_train":[0.31,0.87,-0.42,1.64],"X_test":[[0.40,-0.20,0.10,0.55,-0.75,0.30,0.95,-0.15],[-1.10,0.85,-0.45,-0.60,0.35,1.05,-0.50,0.25]]}
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
model | Name of the fine-tuned model, the training job's model_name | ft- then 1 to 60 lowercase letters, digits and -, the first a letter or digit | Yes |
X_train | Labeled context rows, shape [n_context][n_features] | Numbers or null; same columns as X_test | Yes |
y_train | Regression target of each X_train row | Finite numbers; one per X_train row | Yes |
X_test | Rows to predict, shape [n_query][n_features] | Same columns and order as X_train | Yes |
task | Task to run | "regression" only; default "regression" | No |
Support
Vendor support
Support is available by email at support@synthefy.com . We assist with subscription, training jobs, deployment, invocation, and functional questions on a best-effort basis, typically responding within two business days. Training jobs and endpoints run in your AWS account, so include the training job name and its FailureReason, or the endpoint name, when you write.
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Synthefy-Nori is a foundation model for tabular data that replaces the train-and-tune workflow: pass your labeled rows as context and get predictions in a single forward pass - no training, tuning, feature engineering, or cross-validation. It achieves the highest mean R2 of any tabular foundation model across 96 public regression datasets and beats tuned gradient boosting (XGBoost/LightGBM) on 9 of 13 TabArena tasks, at just 6M parameters. It deploys as an Amazon SageMaker endpoint that runs entirely within your own AWS account.
Foundation model for time series forecasting with contextual metadata.
AI Refinery™ is an AI foundation platform, created by Accenture and built to leverage NVIDIA technology to help companies turn raw AI technology into useful business solutions.
o Agents - Build agents and create an autonomous network that works together to accomplish goals.
o Knowledge - Collect and organize enterprise data and knowledge to power AI applications and agents.
o Models - Customize pre-built foundation models using proprietary data, and flex between models based on key performance factors.
o Governance - Manage all AI components across an enterprise, with an eye on cost, accuracy, security, responsible use, and more.
Built for an era where AI defines new processes, workflows, and software, AI Refinery™ puts AI into the hands of an organization's entire workforce to continuously reinvent the highest value enterprise capabilities.
New State-of-the-Art Multilingual Embeddings With Task LoRA
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.