Bring your data
Upload your dataset, validate the format, and create your training and evaluation splits.
support_conversations.jsonlPrepare a dataset, configure a training run, compare the result, and deploy an endpoint. Forgedata connects each stage so you can iterate on your model without rebuilding your infrastructure.
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/completionsGather examples of the behavior you want: support conversations, structured outputs, domain knowledge, or preferred writing style. Upload CSV or JSONL, review validation, and create an evaluation split.
{"messages": [
{"role": "system",
"content": "You are a product expert."},
{"role": "user",
"content": "Explain our deployment options."},
{"role": "assistant",
"content": "Choose a dedicated endpoint..."}
]} Example conversation formatSelect a foundation model and LoRA or QLoRA settings. Review training loss and checkpoints, then compare your model against its baseline using examples the model has never seen.
Use task specific evaluation. A lower training loss alone does not prove that a model is ready for your application.
Choose a model version and provision an endpoint. Call it from your application using a familiar API format, then track usage as you prepare your next iteration.
Request accessresponse = client.chat.completions.create(
model="your-custom-model",
messages=[
{"role": "user", "content": "Hello"}
]
)
print(response.choices[0].message.content)Illustrative API · Early accessForgedata 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