Train without the GPU setup.
Adapt open models with LoRA and QLoRA. Spend your time improving results, not configuring training infrastructure.
Adapt an open model to your support workflow. Explore LoRA training and policy-specific evaluation, with hosted training and API deployment on the product roadmap.
conversations.jsonl CSV · JSONL
LoRA / QLoRA NVIDIA GPU
POST /v1/chat/completions
Watch an illustrated guide to preparing data, adapting an open model, and evaluating it before a planned API release.
Illustrated product workflow. Shows the intended experience. Hosted training and API deployment are planned.
See the actual local experiment64 synthetic training tickets. A saved adapter. All 16 test outputs. The candidate returned valid JSON but missed the routing threshold, so promotion was blocked.
Local Apple MPS run. Synthetic data only. NVIDIA execution and customer validation remain unverified.
Planned model ecosystem · Model availability and licenses vary
Keep datasets, training runs, evaluations, and endpoints together. Give your team a repeatable path from a first experiment to an application integration.
Adapt open models with LoRA and QLoRA. Spend your time improving results, not configuring training infrastructure.
Build on open model foundations with your own datasets and adapters. Keep control of what makes your AI different.
Connect each checkpoint to its dataset, training configuration, and evaluation. Keep the information your team needs to reproduce a result.
Move from a model checkpoint to an API endpoint, with an integration pattern your developers already know.
Prepare examples, adapt a foundation model, and validate the result before you put it in front of users.
Upload your dataset, validate the format, and create your training and evaluation splits.
support_conversations.jsonlChoose an open model, configure LoRA, and follow every training step in your workspace.
method: qlora · epochs: 3Evaluate your model and connect your application to a dedicated inference endpoint.
POST /v1/chat/completionsThe platform architecture targets NVIDIA GPUs for CUDA accelerated training and inference. Configure model runs in a workspace instead of assembling GPU environments for every experiment.
NVIDIA NIM, NeMo, and TensorRT-LLM integrations are on the roadmap.
Fine-tuning is useful when you need consistent behavior, a specific output format, or domain language that a generic prompt cannot reliably deliver.
Train on examples of your schema so applications can work with predictable classifications, fields, and response formats.
Explore the workflowAdapt an open model to the tone, terminology, and resolution patterns in your approved support conversations.
Explore the workflowUse curated examples to improve task behavior in your domain. Combine with retrieval when your application needs current facts.
Explore the workflowForgedata is an AI product platform being built to bring dataset management, parameter efficient fine-tuning, model evaluation, and inference deployment into one workspace. Request early access to discuss current availability.
The planned model catalog includes the Llama, Mistral, Qwen, and Gemma families. Specific model versions and available GPU configurations will be confirmed during early access. Base model licenses continue to apply.
The platform workflow is designed for JSONL and CSV datasets, with schema validation and training and evaluation splits before a job starts.
Model ownership and export are core product goals. Your rights to adapters and weights remain subject to the base model license and the final platform agreement.
The architecture targets CUDA accelerated training on NVIDIA GPUs. TensorRT-LLM optimization, NVIDIA NIM deployment, and NeMo evaluation are planned integrations, on the platform roadmap.
Request early access to confirm endpoint availability for your workload. The interactive preview shows the intended API workflow; it does not provision a live endpoint.
Bring a use case. Explore a model workflow built for your team.
Request access