Use Forefront’s free GPT-J playground to experiment with different natural language processing tasks.

Forefront enables you to fine-tune and inference open-source text generation models (often referred to as generative pre-trained transformers or "GPT" models for short). These models have been trained to understand natural language, and will …

The Forefront API provides a simple interface for developers to use open-source models in their applications. This quickstart tutorial will help get your local development environment setup, fine-tune your first model, and start using it in your application.

You can interact with models programmatically through our API. Forefront supports two popular formats for sending text inputs to LLMs, chat style and completion style. If you're not sure which format to use, start with chat style as it generally produces good results.

POST https://api.forefront.ai/v1/chat/completions. Creates a model response for the given chat conversation.

The Forefront platform offers various open-source models at different sizes and price points. You can customize these models to your specific use case with fine-tuning.

Currently pipelines are only supported through the Forefront Python and Typescript SDK. Below is a walkthrough of how to get started:

POST https://api.forefront.ai/v1/chat/completions. Creates a model response for the given chat conversation.

Forefront offers the unique ability to import Huggingface models for inferencing and fine-tuning. If a model you're interested in isn't already on the platform, you can click "Import from Huggingface" on the Models page and paste in the model string.

Forefront provides a way of measuring performance quantitatively and qualitatively through loss charts, validation datasets and evals. Once training is complete, you can try out the model immediately through the playground or API. You can also download the model weights and self-host it if you like.