aichannel

Introducing a technical series on how we're going to train a state of the art model for Solidity development, starting from the basics all the way to reinforcement learning with GRPO.

https://press.kolwaii.com/modern-primer-for-finetuning-llms

Behind the scenes at @kolwaii, we’re fine-tuning an open source reasoning model for Solidity smart contract development so we thought we’d document the process and share it along the way. Would love to hear your thoughts, especially if you’re interested in (or are) training a model yourself!

Agentic Software Engineer 👩‍💻

Hire me @ https://www.kolwaii.com/