Downloads Β· 30 days
7
39% of all-time downloads
austain/affine-model
affine-model is a machine learning model from austain. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads Β· 30 days
7
39% of all-time downloads
All-time downloads
18
Public
Parameters
4B
8.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.1 GB Β· 100%
From the Hugging Face model README
Mine open reasoning.
Affine Discord | Live Dashboard
Affine is an incentivized RL environment that pays miners who make incremental improvements on a set of tasks (such as program abduction or coding). The mechanism is sybil-proof, decoy-proof, copy-proof, and overfitting-proof.
How does Affine work?
Affine validators incentivize miners to submit models to Subnet 64 on Bittensor (a.k.a Chutes) where they are inference load balanced and publicly available. These models are evaluated on a set of RL environments, with validators looking for models that dominate the Pareto frontierβnamely, models that outcompete all other models across all environments. The network uses a winners-take-all mechanism where miners are incentivized to copy, download, and improve the Pareto frontier model.
Why Affine?
Directed incentives for RL have never been achieved. The ability to direct intelligence and aggregate the work effort of a large, non-permissioned group of individuals on RL tasks will unlock rapid advancement in intelligence. We intend to commoditize reasoning (intelligence's highest form) and break the intelligence sound barrier.
# Install uv package manager
curl -LsSf https://astral.sh/uv/install.sh | sh
# Clone and install Affine
git clone https://github.com/AffineFoundation/affine.git
cd affine
uv venv && source .venv/bin/activate && uv pip install -e .
# Verify installation
af
Affine uses Affinetes for container orchestration, providing:
All evaluation environments are packaged as pre-built Docker images, eliminating the need for complex sandbox management.
Learn how to:
π Complete Validator Guide β
Learn how to:
Affine can be used as an SDK for evaluating models across different environments.
Examples:
examples/sdk.py - Evaluate miners from the network on DED-V2 and ABD-V2 environmentsexamples/sdk2.py - Evaluate custom models by specifying model parameters directlyKey Features:
See the example files for complete usage patterns.