Russ Salakhutdinov Vests Stratum Lora Tokens From Initial Pool
Reactions from ranked influencers
6 posts
I've also vested the tokens that I got from the initial pool for a few months. https://app.streamflow.finance/contract/solana/mainnet/9UdsSLDvVKBFTYWzbYXiEdadnpPVWDqXW9PBKC7fhKL5?new
4) How to use it: Head over to https://stratumlora.com/#providers to contribute. The rewards will be paid out in the native $STRAT token. You can find it at https://pump.fun/coin/7qpVJ9P4KtYs2MeVMYov1tRWRNXKFbYYtXrxpqptpump Once you install the Trainer you enter your Solana wallet and it will start working and sending rewards on every run. There are four options ( Fast, Normal, Eco and Relaxed ) Feel free to chose the option that suits your workflow it will auto start on Fast which is the most intensive but can be easily changed in settings.
3) Why I built it: 1. Fine-tuning at scale still needs compute most people don't have alone 2. Thousands of small shards ≈ one community run, with checkpoints everyone owns Its also a fun experiment
2) Stratum is built on a different premise: open weights, forged together. Contributors install a CLI, connect their GPU, and pull LoRA/SFT shard jobs from a coordinator. Each machine trains a small adapter. The coordinator merges shards into public checkpoints you can download from the dashboard. Every user also has a @Solana wallet tied to their identity and get paid rewards in the the $STRAT token that I have made.
People are asking me what the $STRAT contract address is please be safe there's only one. https://pump.fun/coin/7qpVJ9P4KtYs2MeVMYov1tRWRNXKFbYYtXrxpqptpump
1) New project: Stratum a proof of work decentralized network for community fine tuning open Kimi weights. The problem is simple: all frontier models are trained behind closed doors. The weights never leave the lab.