--- license: apache-2.0 pipeline_tag: image-text-to-text tags: - prism - neural-architecture-search - multimodal - under-development ---
![BASE-1 Banner](https://github.com/PlatformNetwork/prism/raw/main/assets/banner.png)

BASE-1

A multimodal foundation model whose architecture is discovered through decentralized neural architecture search

[![PRISM](https://img.shields.io/badge/Built%20with-PRISM-6f42c1.svg)](https://github.com/PlatformNetwork/prism) [![Status](https://img.shields.io/badge/Status-In%20Development-orange.svg)]() [![Modality](https://img.shields.io/badge/Modality-Text%20%2F%20Image%20%E2%86%92%20Text-blue.svg)]() [![License](https://img.shields.io/badge/License-Apache%202.0-green.svg)](https://www.apache.org/licenses/LICENSE-2.0)
--- ## Status: In Development BASE-1 is currently under active development. No weights are available yet. This repository will host the model checkpoints, configuration, and usage documentation once the architecture search and training phases are complete. ## Model Summary | | | |---|---| | **Developer** | [Cortex Foundation](https://cortex.foundation) in partnership with [Platform](https://platform.network) | | **Architecture** | Determined by neural architecture search (in progress) | | **Parameters** | To be announced after architecture search | | **Input modalities** | Text, Image | | **Output modality** | Text | | **Architecture search** | [PRISM](https://github.com/PlatformNetwork/prism) — decentralized NAS on the Platform Network | | **License** | Apache 2.0 | ## Overview BASE-1 is a foundation model being developed through [PRISM](https://github.com/PlatformNetwork/prism), a decentralized neural architecture search (NAS) challenge running on the Platform Network. Rather than committing to a hand-designed architecture upfront, BASE-1's design is discovered competitively: miners across the network submit novel architecture families and training recipes, which are evaluated in isolated benchmark environments for learning quality, training stability, and scaling behavior. The best-performing architecture that emerges from this search will be used to train BASE-1 at scale. ### How the architecture is discovered PRISM fixes the dataset and evaluation protocol, not the search space. Candidate submissions are scored on: - **Learning quality** — proxy loss performance under a shared, deterministic evaluation contract - **Training stability** — smooth loss curves, stable gradients, and well-behaved activations - **Scaling signals** — consistent improvements across model size, depth, sequence length, and batch scaling - **Noise resistance** — dynamic thresholds prevent marginal random fluctuations from being rewarded as improvements Architecture discovery and training-recipe improvements (optimizer, loss computation, inference, train step) are attributed and rewarded independently, so both the model design and its training procedure are optimized by the network. ## Modalities BASE-1 will support **Text/Image to Text**: it will accept text and images as input and generate text as output. | Input | Output | |-------|--------| | Text | Text | | Image | Text | ## Why is the model size not announced? The parameter count of BASE-1 is genuinely not decided yet — and this is by design. In a conventional training pipeline, the architecture and parameter budget are fixed first, then training begins. BASE-1 inverts this process: 1. **Architecture search comes first.** PRISM evaluates candidate architectures at compact proxy scales, measuring loss curves, gradient stability, activation behavior, and how performance evolves across model size, depth, sequence length, and batch size. 2. **Scaling laws are derived from the winning architecture.** Each architecture family exhibits its own scaling behavior. The optimal parameter count depends on the scaling-law signals of the architecture that wins the search — a number that cannot be known before the search concludes. 3. **The final size is chosen from evidence, not convention.** Once the winning architecture's scaling characteristics are measured, the parameter budget will be set where the compute/performance trade-off is optimal for that specific design. The final model size will be announced once the architecture search is complete. ## Roadmap | Phase | Description | Status | |-------|-------------|--------| | 1. PRISM challenge launch | Open the decentralized architecture search to miners on the Platform Network | In progress | | 2. Architecture selection | Identify the best-performing architecture family from competitive evaluation and scaling analysis | Pending | | 3. Dataset curation | Assemble and validate the large-scale multimodal training corpus | Pending | | 4. Large-scale training | Train BASE-1 at the parameter budget derived from the winning architecture's scaling laws | Pending | | 5. Model release | Publish weights, configuration, evaluation results, and usage documentation in this repository | Pending | ## Intended Use BASE-1 is intended as a general-purpose multimodal foundation model for text generation conditioned on text and image inputs. Detailed intended-use guidance, limitations, and evaluation results will be published with the model release. ## Evaluation Benchmark results will be published alongside the weights once training is complete. Architecture-search-stage evaluations follow the PRISM scoring protocol, documented in [Scoring and rewards](https://github.com/PlatformNetwork/prism/blob/main/docs/scoring.md) and [Scaling evaluation](https://github.com/PlatformNetwork/prism/blob/main/docs/scaling.md). ## Resources - PRISM (architecture search): [github.com/PlatformNetwork/prism](https://github.com/PlatformNetwork/prism) - PRISM documentation: [Overview](https://github.com/PlatformNetwork/prism/blob/main/docs/overview.md) | [Architecture](https://github.com/PlatformNetwork/prism/blob/main/docs/architecture.md) | [Scoring](https://github.com/PlatformNetwork/prism/blob/main/docs/scoring.md) | [Scaling](https://github.com/PlatformNetwork/prism/blob/main/docs/scaling.md) - Platform Network: [platform.network](https://platform.network) ## License This repository is released under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0).